Model profile · Google

gemini-3.8-flash-high

Closed weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

Reads as thin verified coverage across the resolved source data. Capability fit excludes speed and cost.

Visible coverage: 50.7%
Verified coverage: 50.7%
Spread: 98.5%
Last verified: Oct 3, 2026

70%capability fit

textcodevisiondocument5 aliases43 official source links

Open compare

Data version

Current snapshot.

Published Oct 3, 2026Model list checked4 stale sources105 claim warnings9 providers · 1334 tracked models

The registry snapshot and page stamp are shown so a stale deploy is visible at a glance. View live data status.

Source-linked scores by benchmark

Each row keeps the benchmark source, source type, raw metric, and percentile inside its fair comparison set. Capability summaries exclude archived categories, speed, and cost; those rows remain below.

Thin verified coverageThis model currently reads as thin verified coverage across the resolved source data.

Chat / text35 benchmarks92.7%

Intelligence Index

AA · Chat / text · Combined

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #47 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 41
Percentile: 91.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

91.7% percentile inside its fair comparison set

41Raw benchmark value

AA-Omniscience accuracy

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #29 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 54.6%
Percentile: 93.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

93.8% percentile inside its fair comparison set

54.6%Raw benchmark value

AA-Omniscience non-hallucination

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #111 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 44.8%
Percentile: 75.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

75.7% percentile inside its fair comparison set

44.8%Raw benchmark value

Input price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #212 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.8 /1M input tokens
Percentile: 41.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

41.2% percentile inside its fair comparison set

$0.8 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #219 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $3.8 /1M output tokens
Percentile: 39%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

39% percentile inside its fair comparison set

$3.8 /1M output tokensRaw benchmark value

Output Speed

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #16 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 248.5 tokens/s
Percentile: 94.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

94.3% percentile inside its fair comparison set

248.5 tokens/sRaw benchmark value

Time to first token

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #208 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 18.95s
Percentile: 21.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

21.6% percentile inside its fair comparison set

18.95sRaw benchmark value

Time to first answer token

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #127 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 18.95s
Percentile: 51.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

51.9% percentile inside its fair comparison set

18.95sRaw benchmark value

Text Arena

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: overall. Source rank: #8. Votes: 26298. Organization: google. License: Proprietary.

98.1% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,490 - 1,500

Text Arena · Creative Writing

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #7 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 98.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: creative_writing. Source rank: #7. Votes: 5697. Organization: google. License: Proprietary.

98.4% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,476 - 1,494

Text Arena · English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: english. Source rank: #10. Votes: 10363. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,491 - 1,505

Text Arena · Exclude Ties

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: exclude_ties. Source rank: #10. Votes: 19429. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,505 - 1,519

Text Arena · Hard Prompts

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #11 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,516
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: hard_prompts. Source rank: #11. Votes: 17137. Organization: google. License: Proprietary.

97.3% percentile inside its fair comparison set

1,516Raw benchmark valueCI 1,510 - 1,522

Text Arena · Hard Prompts English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #17 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: hard_prompts_english. Source rank: #17. Votes: 6715. Organization: google. License: Proprietary.

95.7% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,504 - 1,520

Text Arena · Instruction Following

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #15 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,486
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: instruction_following. Source rank: #15. Votes: 9459. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,486Raw benchmark valueCI 1,479 - 1,493

Text Arena · Longer Query

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,509
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: longer_query. Source rank: #8. Votes: 12354. Organization: google. License: Proprietary.

98% percentile inside its fair comparison set

1,509Raw benchmark valueCI 1,502 - 1,515

Text Arena · Multi Turn

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,501
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: multi_turn. Source rank: #8. Votes: 4004. Organization: google. License: Proprietary.

98.1% percentile inside its fair comparison set

1,501Raw benchmark valueCI 1,490 - 1,511

Text Arena · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: overall. Source rank: #8. Votes: 26298. Organization: google. License: Proprietary.

98.1% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,492 - 1,502

Text Arena · Creative Writing · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: creative_writing. Source rank: #8. Votes: 5697. Organization: google. License: Proprietary.

98.1% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,480 - 1,498

Text Arena · English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: english. Source rank: #10. Votes: 10363. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,491 - 1,505

Text Arena · Exclude Ties · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: exclude_ties. Source rank: #8. Votes: 19429. Organization: google. License: Proprietary.

98.1% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,505 - 1,519

Text Arena · Hard Prompts · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,507
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: hard_prompts. Source rank: #10. Votes: 17137. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,507Raw benchmark valueCI 1,500 - 1,513

Text Arena · Hard Prompts English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #13 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,502
Percentile: 96.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: hard_prompts_english. Source rank: #13. Votes: 6715. Organization: google. License: Proprietary.

96.8% percentile inside its fair comparison set

1,502Raw benchmark valueCI 1,494 - 1,510

Text Arena · Instruction Following · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #13 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 96.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: instruction_following. Source rank: #13. Votes: 9459. Organization: google. License: Proprietary.

96.8% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,480 - 1,494

Text Arena · Longer Query · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #9 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 97.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: longer_query. Source rank: #9. Votes: 12354. Organization: google. License: Proprietary.

97.7% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,499 - 1,513

Text Arena · Multi Turn · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: multi_turn. Source rank: #10. Votes: 4004. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,489 - 1,509

Instruction following

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 81.4%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: IF. Tasks scored: 4.

100% percentile inside its fair comparison set

81.4%Raw benchmark value

Language

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #7 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 87.8%
Percentile: 90.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Language. Tasks scored: 3.

90.8% percentile inside its fair comparison set

87.8%Raw benchmark value

Paraphrase

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: paraphrase. Category: IF.

100% percentile inside its fair comparison set

80%Raw benchmark value

Simplify

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.4%
Percentile: 98.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: simplify. Category: IF.

98.5% percentile inside its fair comparison set

75.4%Raw benchmark value

Story generation

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82.8%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: story_generation. Category: IF.

100% percentile inside its fair comparison set

82.8%Raw benchmark value

Summarize

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 87.5%
Percentile: 98.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: summarize. Category: IF.

98.5% percentile inside its fair comparison set

87.5%Raw benchmark value

Connections

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #13 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 100%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: connections. Category: Language.

100% percentile inside its fair comparison set

100%Raw benchmark value

Plot unscrambling

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #13 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.4%
Percentile: 81.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: plot_unscrambling. Category: Language.

81.5% percentile inside its fair comparison set

73.4%Raw benchmark value

Typos

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #5 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 90%
Percentile: 95.4%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: typos. Category: Language.

95.4% percentile inside its fair comparison set

90%Raw benchmark value

Coding22 benchmarks61.2%

SciCode

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #27 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 56.6%
Percentile: 86.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

86.9% percentile inside its fair comparison set

56.6%Raw benchmark value

HiL-Bench

SL · Coding · Rubric

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #6 · Source label: Gemini 3.8 Flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 41.5%
Percentile: 68.8%
Last updated: recent
Eligibility: headline eligible

Parsed from the public Scale Labs page for scale-hil-bench. Reported model configuration: Gemini 3.8 Flash. Collapse policy: highest reported score per canonical model.

68.8% percentile inside its fair comparison set

41.5%Raw benchmark value

Text Arena · Coding

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #22 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,530
Percentile: 94.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: coding. Source rank: #22. Votes: 7067. Organization: google. License: Proprietary.

94.3% percentile inside its fair comparison set

1,530Raw benchmark valueCI 1,522 - 1,538

Text Arena · Coding · No Style Control

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #16 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,509
Percentile: 96%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: coding. Source rank: #16. Votes: 7067. Organization: google. License: Proprietary.

96% percentile inside its fair comparison set

1,509Raw benchmark valueCI 1,502 - 1,517

Vibe Code Bench v1.1

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #22 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 78.7%
Percentile: 77.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vibe-code; provider: Google.

77.4% percentile inside its fair comparison set

78.7%Raw benchmark valueCI 71% - 86.3%

WebDev Arena

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #28 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,583
Percentile: 78.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: overall. Source rank: #29. Votes: 8524. Organization: google. License: Proprietary.

78.7% percentile inside its fair comparison set

1,583Raw benchmark valueCI 1,575 - 1,591

Code Arena · Webdev Html

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #17 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,621
Percentile: 87.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: webdev-html. Source rank: #18. Votes: 1208. Organization: google. License: Proprietary.

87.2% percentile inside its fair comparison set

1,621Raw benchmark valueCI 1,602 - 1,640

Code Arena · Webdev React

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #31 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,576
Percentile: 73.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: webdev-react. Source rank: #32. Votes: 5551. Organization: google. License: Proprietary.

73.5% percentile inside its fair comparison set

1,576Raw benchmark valueCI 1,566 - 1,585

Code Migration

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #32 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 36.5%
Percentile: 54.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: code-migration; provider: Google.

54.4% percentile inside its fair comparison set

36.5%Raw benchmark valueCI 28.3% - 44.7%

IOI

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #17 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 56.9%
Percentile: 56.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: ioi; provider: Google.

56.8% percentile inside its fair comparison set

56.9%Raw benchmark valueCI 52.5% - 61.4%

ProgramBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #16 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 1%
Percentile: 77.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: programbench; provider: Google.

77.6% percentile inside its fair comparison set

1%Raw benchmark valueCI 0% - 2.4%

Terminal-Bench 2.1

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #8 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 81.3%
Percentile: 89.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Google.

89.6% percentile inside its fair comparison set

81.3%Raw benchmark valueCI 80.5% - 82%

Terminal-Bench 4.0

TERMINAL-BENCH · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #23 · Source label: Gemini 3.8 Flash (high)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 19.1%
Percentile: 15.4%
Last updated: recent
Eligibility: headline eligible

Parsed from the public Terminal-Bench 4.0 official published leaderboard (status: display). Collapse policy: highest verified score per canonical model. Selected agent: mini-SWE-agent. Display model: Gemini 3.8 Flash. Agent URL: https://github.com/SWE-agent/mini-swe-agent. Reported stderr: 1.714 percentage points.

15.4% percentile inside its fair comparison set

19.1%Raw benchmark valueCI 15.7% - 22.5%

SWE-bench Verified

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #23 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 80%
Percentile: 73.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: swebench; provider: Google.

73.2% percentile inside its fair comparison set

80%Raw benchmark valueCI 76.5% - 83.5%

LiveCodeBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #3 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.5%
Percentile: 98.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: lcb; provider: Google.

98.4% percentile inside its fair comparison set

89.5%Raw benchmark valueCI 87.7% - 91.2%

Agentic coding

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #31 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 54.2%
Percentile: 53.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Agentic Coding. Tasks scored: 3.

53.8% percentile inside its fair comparison set

54.2%Raw benchmark value

Coding

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #54 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 72.5%
Percentile: 18.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Coding. Tasks scored: 2.

18.5% percentile inside its fair comparison set

72.5%Raw benchmark value

JavaScript

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #13 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 72.7%
Percentile: 87.7%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: javascript. Category: Agentic Coding.

87.7% percentile inside its fair comparison set

72.7%Raw benchmark value

TypeScript

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #35 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 40%
Percentile: 47.7%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: typescript. Category: Agentic Coding.

47.7% percentile inside its fair comparison set

40%Raw benchmark value

Python

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #51 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 50%
Percentile: 46.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: python. Category: Agentic Coding.

46.2% percentile inside its fair comparison set

50%Raw benchmark value

Coding generation

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #54 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.2%
Percentile: 21.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: code_generation. Category: Coding.

21.5% percentile inside its fair comparison set

73.2%Raw benchmark value

Coding completion

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #55 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 71.7%
Percentile: 18.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: code_completion. Category: Coding.

18.5% percentile inside its fair comparison set

71.7%Raw benchmark value

Reasoning / math / science18 benchmarks81%

Humanity's Last Exam

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #33 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.8%
Percentile: 94%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

94% percentile inside its fair comparison set

47.8%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #3 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 95.3%
Percentile: 99.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

99.6% percentile inside its fair comparison set

95.3%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #48 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 18.3%
Percentile: 89.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

89.7% percentile inside its fair comparison set

18.3%Raw benchmark value

Text Arena · Math

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #5 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: math. Source rank: #5. Votes: 1274. Organization: google. License: Proprietary.

98.9% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,501 - 1,534

Text Arena · Math · No Style Control

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #4 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,523
Percentile: 99.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: math. Source rank: #4. Votes: 1274. Organization: google. License: Proprietary.

99.2% percentile inside its fair comparison set

1,523Raw benchmark valueCI 1,506 - 1,540

ProofBench

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #27 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 48%
Percentile: 38.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: proof_bench; provider: Google.

38.1% percentile inside its fair comparison set

48%Raw benchmark valueCI 38.2% - 57.8%

GPQA Diamond

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #4 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 94.4%
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: gpqa; provider: Google.

97.6% percentile inside its fair comparison set

94.4%Raw benchmark valueCI 91.5% - 97.3%

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #5 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 90.2%
Percentile: 96.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmlu_pro; provider: Google.

96.8% percentile inside its fair comparison set

90.2%Raw benchmark valueCI 89.6% - 90.8%

Mathematics

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #26 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 91.6%
Percentile: 61.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Mathematics. Tasks scored: 4.

61.5% percentile inside its fair comparison set

91.6%Raw benchmark value

Reasoning

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #18 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 89.3%
Percentile: 73.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Reasoning. Tasks scored: 4.

73.8% percentile inside its fair comparison set

89.3%Raw benchmark value

AMPS Hard

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #9 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 99%
Percentile: 98.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: AMPS_Hard. Category: Mathematics.

98.5% percentile inside its fair comparison set

99%Raw benchmark value

Integrals with game

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #32 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80%
Percentile: 53.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: integrals_with_game. Category: Mathematics.

53.8% percentile inside its fair comparison set

80%Raw benchmark value

Math competition

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #48 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 95.1%
Percentile: 49.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: math_comp. Category: Mathematics.

49.2% percentile inside its fair comparison set

95.1%Raw benchmark value

Olympiad

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 92.2%
Percentile: 86.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: olympiad. Category: Mathematics.

86.2% percentile inside its fair comparison set

92.2%Raw benchmark value

Theory of mind

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #47 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76.9%
Percentile: 33.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: theory_of_mind. Category: Reasoning.

33.8% percentile inside its fair comparison set

76.9%Raw benchmark value

Zebra puzzle

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #23 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98.3%
Percentile: 67.7%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: zebra_puzzle. Category: Reasoning.

67.7% percentile inside its fair comparison set

98.3%Raw benchmark value

Spatial

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #17 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 100%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: spatial. Category: Reasoning.

100% percentile inside its fair comparison set

100%Raw benchmark value

Logic with navigation

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #12 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82%
Percentile: 86.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: logic_with_navigation. Category: Reasoning.

86.2% percentile inside its fair comparison set

82%Raw benchmark value

Professional reasoning35 benchmarks56%

PRBench Legal

SL · Professional reasoning · Rubric

Applied legal reasoning on professional-domain tasks.

Rank #13 · Source label: Gemini 3.8 Flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 48.9%
Percentile: 70.7%
Last updated: recent
Eligibility: headline eligible

Parsed from the public Scale Labs page for scale-prbench-legal. Reported model configuration: Gemini 3.8 Flash. Collapse policy: highest reported score per canonical model.

70.7% percentile inside its fair comparison set

48.9%Raw benchmark value

Text Arena · Expert

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #16 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,526
Percentile: 95.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: expert. Source rank: #16. Votes: 3109. Organization: google. License: Proprietary.

95.4% percentile inside its fair comparison set

1,526Raw benchmark valueCI 1,515 - 1,537

Text Arena · Industry Business And Management And Financial Operations

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #25 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 93.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_business_and_management_and_financial_operations. Source rank: #26. Votes: 4900. Organization: google. License: Proprietary.

93.5% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,472 - 1,490

Text Arena · Industry Entertainment And Sports And Media

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,471
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #10. Votes: 6903. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,471Raw benchmark valueCI 1,463 - 1,480

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #23 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 93.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_legal_and_government. Source rank: #23. Votes: 2385. Organization: google. License: Proprietary.

93.7% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,480 - 1,505

Text Arena · Industry Life And Physical And Social Science

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_life_and_physical_and_social_science. Source rank: #10. Votes: 4290. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,508 - 1,527

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #11 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 97.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_mathematical. Source rank: #11. Votes: 1506. Organization: google. License: Proprietary.

97.2% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,496 - 1,528

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,510
Percentile: 97.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_medicine_and_healthcare. Source rank: #10. Votes: 1840. Organization: google. License: Proprietary.

97.4% percentile inside its fair comparison set

1,510Raw benchmark valueCI 1,496 - 1,525

Text Arena · Industry Software And It Services

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #23 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 94.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_software_and_it_services. Source rank: #23. Votes: 10103. Organization: google. License: Proprietary.

94.1% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,510 - 1,523

Text Arena · Industry Writing And Literature And Language

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #9 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 97.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_writing_and_literature_and_language. Source rank: #9. Votes: 7274. Organization: google. License: Proprietary.

97.9% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,479 - 1,495

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #11 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,527
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: expert. Source rank: #11. Votes: 3109. Organization: google. License: Proprietary.

96.9% percentile inside its fair comparison set

1,527Raw benchmark valueCI 1,516 - 1,538

Text Arena · Industry Business And Management And Financial Operations · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #12 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 97%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_business_and_management_and_financial_operations. Source rank: #12. Votes: 4900. Organization: google. License: Proprietary.

97% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,471 - 1,489

Text Arena · Industry Entertainment And Sports And Media · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,474
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #10. Votes: 6903. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,474Raw benchmark valueCI 1,466 - 1,482

Text Arena · Industry Legal And Government · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #12 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 96.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_legal_and_government. Source rank: #12. Votes: 2385. Organization: google. License: Proprietary.

96.8% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,486 - 1,511

Text Arena · Industry Life And Physical And Social Science · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #6 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,521
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_life_and_physical_and_social_science. Source rank: #6. Votes: 4290. Organization: google. License: Proprietary.

98.7% percentile inside its fair comparison set

1,521Raw benchmark valueCI 1,511 - 1,530

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #7 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,518
Percentile: 98.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_mathematical. Source rank: #7. Votes: 1506. Organization: google. License: Proprietary.

98.3% percentile inside its fair comparison set

1,518Raw benchmark valueCI 1,502 - 1,534

Text Arena · Industry Medicine And Healthcare · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #5 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,509
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_medicine_and_healthcare. Source rank: #5. Votes: 1840. Organization: google. License: Proprietary.

98.8% percentile inside its fair comparison set

1,509Raw benchmark valueCI 1,495 - 1,524

Text Arena · Industry Software And It Services · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #14 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 96.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_software_and_it_services. Source rank: #14. Votes: 10103. Organization: google. License: Proprietary.

96.5% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,498 - 1,512

Text Arena · Industry Writing And Literature And Language · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #11 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_writing_and_literature_and_language. Source rank: #11. Votes: 7274. Organization: google. License: Proprietary.

97.3% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,482 - 1,498

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #15 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 55
Percentile: 65%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vals_index; provider: Google.

65% percentile inside its fair comparison set

55Raw benchmark valueCI 53 - 57

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #26 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 38.9%
Percentile: 63.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_research; provider: Google.

63.2% percentile inside its fair comparison set

38.9%Raw benchmark valueCI 32.3% - 45.6%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

Completing legal work with documents, spreadsheets, presentations, and file-system tools.

Rank #14 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 10%
Percentile: 81.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: hlab; provider: Google.

81.2% percentile inside its fair comparison set

10%Raw benchmark valueCI 5.3% - 14.7%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #7 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87%
Percentile: 95.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_bench; provider: Google.

95.6% percentile inside its fair comparison set

87%Raw benchmark valueCI 86.1% - 87.8%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #2 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 61.4%
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: fabv2; provider: Google.

98.6% percentile inside its fair comparison set

61.4%Raw benchmark valueCI 61.2% - 61.7%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #29 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 48.1%
Percentile: 70.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medcode; provider: Google.

70.5% percentile inside its fair comparison set

48.1%Raw benchmark valueCI 43.9% - 52.4%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #32 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84.5%
Percentile: 67.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medscribe; provider: Google.

67.7% percentile inside its fair comparison set

84.5%Raw benchmark valueCI 80.7% - 88.3%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #65 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 35.1%
Percentile: 21%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: sage; provider: Google.

21% percentile inside its fair comparison set

35.1%Raw benchmark valueCI 28.5% - 41.7%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #19 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.3%
Percentile: 60%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: public-benefits-bench; provider: Google.

60% percentile inside its fair comparison set

65.3%Raw benchmark valueCI 62.9% - 67.7%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #11 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 58%
Percentile: 69.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: skillsbench; provider: Google.

69.7% percentile inside its fair comparison set

58%Raw benchmark valueCI 49.3% - 66.7%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #36 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74.4%
Percentile: 72.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

72.9% percentile inside its fair comparison set

74.4%Raw benchmark valueCI 72.8% - 76.1%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #65 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 54%
Percentile: 1.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Data Analysis. Tasks scored: 3.

1.5% percentile inside its fair comparison set

54%Raw benchmark value

Overall

LB · Professional reasoning · Objective

Average objective performance across LiveBench's current public category mix.

Rank #34 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.8%
Percentile: 49.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category averages included: 7.

49.2% percentile inside its fair comparison set

75.8%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #65 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 20.6%
Percentile: 1.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: consecutive_events. Category: Data Analysis.

1.5% percentile inside its fair comparison set

20.6%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #54 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45.3%
Percentile: 18.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: tablejoin. Category: Data Analysis.

18.5% percentile inside its fair comparison set

45.3%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #61 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.1%
Percentile: 20%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: tablereformat. Category: Data Analysis.

20% percentile inside its fair comparison set

96.1%Raw benchmark value

Long context1 benchmark92.1%

Long Context Reasoning

AA · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #39 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 81.3%
Percentile: 92.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

92.1% percentile inside its fair comparison set

81.3%Raw benchmark value

Vision understanding14 benchmarks95.1%

MMMU-Pro

AA · Vision understanding · Objective

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #9 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 85.6%
Percentile: 96.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

96.2% percentile inside its fair comparison set

85.6%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #11 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,290
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: overall. Source rank: #11. Votes: 3086. Organization: google. License: Proprietary.

92.8% percentile inside its fair comparison set

1,290Raw benchmark valueCI 1,279 - 1,302

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #32 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,255
Percentile: 62.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: creative_writing_vision. Source rank: #37. Votes: 284. Organization: google. License: Proprietary.

62.2% percentile inside its fair comparison set

1,255Raw benchmark valueCI 1,219 - 1,292

Vision Arena · Diagram

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #2 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,341
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: diagram. Source rank: #2. Votes: 793. Organization: google. License: Proprietary.

99% percentile inside its fair comparison set

1,341Raw benchmark valueCI 1,319 - 1,363

Vision Arena · English

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,291
Percentile: 94.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: english. Source rank: #8. Votes: 1010. Organization: google. License: Proprietary.

94.9% percentile inside its fair comparison set

1,291Raw benchmark valueCI 1,271 - 1,310

Vision Arena · Homework

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #7 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,334
Percentile: 93.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: homework. Source rank: #7. Votes: 418. Organization: google. License: Proprietary.

93.8% percentile inside its fair comparison set

1,334Raw benchmark valueCI 1,305 - 1,362

Vision Arena · Ocr

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #3 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,315
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: ocr. Source rank: #3. Votes: 2081. Organization: google. License: Proprietary.

98% percentile inside its fair comparison set

1,315Raw benchmark valueCI 1,301 - 1,329

Vision Arena · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #5 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,316
Percentile: 97.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: overall. Source rank: #5. Votes: 3086. Organization: google. License: Proprietary.

97.1% percentile inside its fair comparison set

1,316Raw benchmark valueCI 1,304 - 1,327

Vision Arena · Creative Writing Vision · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #25 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,280
Percentile: 70.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: creative_writing_vision. Source rank: #28. Votes: 284. Organization: google. License: Proprietary.

70.7% percentile inside its fair comparison set

1,280Raw benchmark valueCI 1,245 - 1,316

Vision Arena · Diagram · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #2 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,353
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: diagram. Source rank: #2. Votes: 793. Organization: google. License: Proprietary.

99% percentile inside its fair comparison set

1,353Raw benchmark valueCI 1,331 - 1,375

Vision Arena · English · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #6 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,318
Percentile: 96.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: english. Source rank: #6. Votes: 1010. Organization: google. License: Proprietary.

96.4% percentile inside its fair comparison set

1,318Raw benchmark valueCI 1,299 - 1,338

Vision Arena · Homework · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #3 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,347
Percentile: 97.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: homework. Source rank: #3. Votes: 418. Organization: google. License: Proprietary.

97.9% percentile inside its fair comparison set

1,347Raw benchmark valueCI 1,319 - 1,376

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #2 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,333
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: ocr. Source rank: #2. Votes: 2081. Organization: google. License: Proprietary.

99% percentile inside its fair comparison set

1,333Raw benchmark valueCI 1,320 - 1,347

MMMU Pro

VALS-AI · Vision understanding · Objective

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #4 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.1%
Percentile: 96.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmmu; provider: Google.

96.4% percentile inside its fair comparison set

89.1%Raw benchmark valueCI 87.6% - 90.5%

Document understanding1 benchmark52.3%

MortgageTax

VALS-AI · Document understanding · Objective

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #42 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.3%
Percentile: 52.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mortgage_tax; provider: Google.

52.3% percentile inside its fair comparison set

65.3%Raw benchmark valueCI 63.5% - 67.2%

Multilingual18 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #14 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,536
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: chinese. Source rank: #14. Votes: 2061. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,536Raw benchmark valueCI 1,522 - 1,550

Text Arena · French

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #18 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 93.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: french. Source rank: #18. Votes: 789. Organization: google. License: Proprietary.

93.4% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,483 - 1,528

Text Arena · German

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #37 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 86.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: german. Source rank: #40. Votes: 398. Organization: google. License: Proprietary.

86.8% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,443 - 1,500

Text Arena · Japanese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #7 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: japanese. Source rank: #7. Votes: 462. Organization: google. License: Proprietary.

97.5% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,473 - 1,533

Text Arena · Korean

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #17 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 93.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: korean. Source rank: #17. Votes: 487. Organization: google. License: Proprietary.

93.4% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,427 - 1,484

Text Arena · Non English

AR · Multilingual · Human

Observed user preference in Arena's Text Arena non_english leaderboard.

Rank #11 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: non_english. Source rank: #11. Votes: 15930. Organization: google. License: Proprietary.

97.3% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,478 - 1,490

Text Arena · Polish

AR · Multilingual · Human

Observed user preference in Arena's Text Arena polish leaderboard.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,501
Percentile: 95.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: polish. Source rank: #10. Votes: 364. Organization: google. License: Proprietary.

95.5% percentile inside its fair comparison set

1,501Raw benchmark valueCI 1,471 - 1,532

Text Arena · Russian

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #5 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,510
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: russian. Source rank: #5. Votes: 3357. Organization: google. License: Proprietary.

98.8% percentile inside its fair comparison set

1,510Raw benchmark valueCI 1,500 - 1,521

Text Arena · Spanish

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #19 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 93.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: spanish. Source rank: #19. Votes: 848. Organization: google. License: Proprietary.

93.1% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,456 - 1,497

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,551
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: chinese. Source rank: #8. Votes: 2061. Organization: google. License: Proprietary.

98% percentile inside its fair comparison set

1,551Raw benchmark valueCI 1,537 - 1,564

Text Arena · French · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #11 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 96.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: french. Source rank: #11. Votes: 789. Organization: google. License: Proprietary.

96.1% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,478 - 1,523

Text Arena · German · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #21 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: german. Source rank: #22. Votes: 398. Organization: google. License: Proprietary.

92.6% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,450 - 1,507

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #7 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: japanese. Source rank: #7. Votes: 462. Organization: google. License: Proprietary.

97.5% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,473 - 1,533

Text Arena · Korean · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 97.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: korean. Source rank: #8. Votes: 487. Organization: google. License: Proprietary.

97.1% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,440 - 1,497

Text Arena · Non English · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena non_english leaderboard.

Rank #7 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 98.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: non_english. Source rank: #7. Votes: 15930. Organization: google. License: Proprietary.

98.4% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,482 - 1,494

Text Arena · Polish · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena polish leaderboard.

Rank #6 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: polish. Source rank: #6. Votes: 364. Organization: google. License: Proprietary.

97.5% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,475 - 1,535

Text Arena · Russian · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #4 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,510
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: russian. Source rank: #4. Votes: 3357. Organization: google. License: Proprietary.

99.1% percentile inside its fair comparison set

1,510Raw benchmark valueCI 1,500 - 1,521

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #12 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 95.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: spanish. Source rank: #12. Votes: 848. Organization: google. License: Proprietary.

95.8% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,464 - 1,505

Source links and registry checks

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

official

LiveBench

Oct 3, 2026

source →

official

Scale Labs

Oct 3, 2026

source →

official

Scale Labs

Oct 3, 2026

source →

official

Terminal-Bench

Oct 3, 2026

source →

Model profile · Google

gemini-3.8-flash-high

Closed weightsmid · registry tag 2026 benchmark-derived

Thin verified coverage

Reads as thin verified coverage across the resolved source data. Capability fit excludes speed and cost.

Visible coverage: 50.7%
Verified coverage: 50.7%
Spread: 98.5%
Last verified: Oct 3, 2026

70%capability fit

textcodevisiondocument5 aliases43 official source links

Open compare

Data version

Current snapshot.

Published Oct 3, 2026Model list checked4 stale sources105 claim warnings9 providers · 1334 tracked models

The registry snapshot and page stamp are shown so a stale deploy is visible at a glance. View live data status.

Source-linked scores by benchmark

Thin verified coverageThis model currently reads as thin verified coverage across the resolved source data.

Chat / text35 benchmarks92.7%

Intelligence Index

AA · Chat / text · Combined

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #47 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 41
Percentile: 91.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

91.7% percentile inside its fair comparison set

41Raw benchmark value

AA-Omniscience accuracy

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #29 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 54.6%
Percentile: 93.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

93.8% percentile inside its fair comparison set

54.6%Raw benchmark value

AA-Omniscience non-hallucination

AA · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #111 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 44.8%
Percentile: 75.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

75.7% percentile inside its fair comparison set

44.8%Raw benchmark value

Input price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #212 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $0.8 /1M input tokens
Percentile: 41.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

41.2% percentile inside its fair comparison set

$0.8 /1M input tokensRaw benchmark value

Output price

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #219 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $3.8 /1M output tokens
Percentile: 39%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

39% percentile inside its fair comparison set

$3.8 /1M output tokensRaw benchmark value

Output Speed

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #16 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 248.5 tokens/s
Percentile: 94.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

94.3% percentile inside its fair comparison set

248.5 tokens/sRaw benchmark value

Time to first token

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #208 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 18.95s
Percentile: 21.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

21.6% percentile inside its fair comparison set

18.95sRaw benchmark value

Time to first answer token

AA · Chat / text · Speed / cost

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #127 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 18.95s
Percentile: 51.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

51.9% percentile inside its fair comparison set

18.95sRaw benchmark value

Text Arena

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: overall. Source rank: #8. Votes: 26298. Organization: google. License: Proprietary.

98.1% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,490 - 1,500

Text Arena · Creative Writing

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #7 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 98.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: creative_writing. Source rank: #7. Votes: 5697. Organization: google. License: Proprietary.

98.4% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,476 - 1,494

Text Arena · English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: english. Source rank: #10. Votes: 10363. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,491 - 1,505

Text Arena · Exclude Ties

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: exclude_ties. Source rank: #10. Votes: 19429. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,505 - 1,519

Text Arena · Hard Prompts

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #11 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,516
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: hard_prompts. Source rank: #11. Votes: 17137. Organization: google. License: Proprietary.

97.3% percentile inside its fair comparison set

1,516Raw benchmark valueCI 1,510 - 1,522

Text Arena · Hard Prompts English

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #17 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: hard_prompts_english. Source rank: #17. Votes: 6715. Organization: google. License: Proprietary.

95.7% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,504 - 1,520

Text Arena · Instruction Following

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #15 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,486
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: instruction_following. Source rank: #15. Votes: 9459. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,486Raw benchmark valueCI 1,479 - 1,493

Text Arena · Longer Query

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,509
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: longer_query. Source rank: #8. Votes: 12354. Organization: google. License: Proprietary.

98% percentile inside its fair comparison set

1,509Raw benchmark valueCI 1,502 - 1,515

Text Arena · Multi Turn

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,501
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: multi_turn. Source rank: #8. Votes: 4004. Organization: google. License: Proprietary.

98.1% percentile inside its fair comparison set

1,501Raw benchmark valueCI 1,490 - 1,511

Text Arena · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: overall. Source rank: #8. Votes: 26298. Organization: google. License: Proprietary.

98.1% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,492 - 1,502

Text Arena · Creative Writing · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: creative_writing. Source rank: #8. Votes: 5697. Organization: google. License: Proprietary.

98.1% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,480 - 1,498

Text Arena · English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: english. Source rank: #10. Votes: 10363. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,491 - 1,505

Text Arena · Exclude Ties · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: exclude_ties. Source rank: #8. Votes: 19429. Organization: google. License: Proprietary.

98.1% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,505 - 1,519

Text Arena · Hard Prompts · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,507
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: hard_prompts. Source rank: #10. Votes: 17137. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,507Raw benchmark valueCI 1,500 - 1,513

Text Arena · Hard Prompts English · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #13 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,502
Percentile: 96.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: hard_prompts_english. Source rank: #13. Votes: 6715. Organization: google. License: Proprietary.

96.8% percentile inside its fair comparison set

1,502Raw benchmark valueCI 1,494 - 1,510

Text Arena · Instruction Following · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #13 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 96.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: instruction_following. Source rank: #13. Votes: 9459. Organization: google. License: Proprietary.

96.8% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,480 - 1,494

Text Arena · Longer Query · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #9 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 97.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: longer_query. Source rank: #9. Votes: 12354. Organization: google. License: Proprietary.

97.7% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,499 - 1,513

Text Arena · Multi Turn · No Style Control

AR · Chat / text · Human

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: multi_turn. Source rank: #10. Votes: 4004. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,489 - 1,509

Instruction following

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 81.4%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: IF. Tasks scored: 4.

100% percentile inside its fair comparison set

81.4%Raw benchmark value

Language

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #7 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 87.8%
Percentile: 90.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Language. Tasks scored: 3.

90.8% percentile inside its fair comparison set

87.8%Raw benchmark value

Paraphrase

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: paraphrase. Category: IF.

100% percentile inside its fair comparison set

80%Raw benchmark value

Simplify

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.4%
Percentile: 98.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: simplify. Category: IF.

98.5% percentile inside its fair comparison set

75.4%Raw benchmark value

Story generation

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #1 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82.8%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: story_generation. Category: IF.

100% percentile inside its fair comparison set

82.8%Raw benchmark value

Summarize

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #2 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 87.5%
Percentile: 98.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: summarize. Category: IF.

98.5% percentile inside its fair comparison set

87.5%Raw benchmark value

Connections

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #13 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 100%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: connections. Category: Language.

100% percentile inside its fair comparison set

100%Raw benchmark value

Plot unscrambling

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #13 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.4%
Percentile: 81.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: plot_unscrambling. Category: Language.

81.5% percentile inside its fair comparison set

73.4%Raw benchmark value

Typos

LB · Chat / text · Objective

It tests whether the model is actually useful in normal conversational turns, not just on narrow correctness tasks.

Rank #5 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 90%
Percentile: 95.4%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: typos. Category: Language.

95.4% percentile inside its fair comparison set

90%Raw benchmark value

Coding22 benchmarks61.2%

SciCode

AA · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #27 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 56.6%
Percentile: 86.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

86.9% percentile inside its fair comparison set

56.6%Raw benchmark value

HiL-Bench

SL · Coding · Rubric

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #6 · Source label: Gemini 3.8 Flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 41.5%
Percentile: 68.8%
Last updated: recent
Eligibility: headline eligible

Parsed from the public Scale Labs page for scale-hil-bench. Reported model configuration: Gemini 3.8 Flash. Collapse policy: highest reported score per canonical model.

68.8% percentile inside its fair comparison set

41.5%Raw benchmark value

Text Arena · Coding

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #22 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,530
Percentile: 94.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: coding. Source rank: #22. Votes: 7067. Organization: google. License: Proprietary.

94.3% percentile inside its fair comparison set

1,530Raw benchmark valueCI 1,522 - 1,538

Text Arena · Coding · No Style Control

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #16 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,509
Percentile: 96%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: coding. Source rank: #16. Votes: 7067. Organization: google. License: Proprietary.

96% percentile inside its fair comparison set

1,509Raw benchmark valueCI 1,502 - 1,517

Vibe Code Bench v1.1

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #22 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 78.7%
Percentile: 77.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vibe-code; provider: Google.

77.4% percentile inside its fair comparison set

78.7%Raw benchmark valueCI 71% - 86.3%

WebDev Arena

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #28 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,583
Percentile: 78.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: overall. Source rank: #29. Votes: 8524. Organization: google. License: Proprietary.

78.7% percentile inside its fair comparison set

1,583Raw benchmark valueCI 1,575 - 1,591

Code Arena · Webdev Html

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #17 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,621
Percentile: 87.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: webdev-html. Source rank: #18. Votes: 1208. Organization: google. License: Proprietary.

87.2% percentile inside its fair comparison set

1,621Raw benchmark valueCI 1,602 - 1,640

Code Arena · Webdev React

AR · Coding · Human

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #31 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,576
Percentile: 73.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: webdev-react. Source rank: #32. Votes: 5551. Organization: google. License: Proprietary.

73.5% percentile inside its fair comparison set

1,576Raw benchmark valueCI 1,566 - 1,585

Code Migration

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #32 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 36.5%
Percentile: 54.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: code-migration; provider: Google.

54.4% percentile inside its fair comparison set

36.5%Raw benchmark valueCI 28.3% - 44.7%

IOI

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #17 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 56.9%
Percentile: 56.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: ioi; provider: Google.

56.8% percentile inside its fair comparison set

56.9%Raw benchmark valueCI 52.5% - 61.4%

ProgramBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #16 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 1%
Percentile: 77.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: programbench; provider: Google.

77.6% percentile inside its fair comparison set

1%Raw benchmark valueCI 0% - 2.4%

Terminal-Bench 2.1

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #8 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 81.3%
Percentile: 89.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: terminal-bench-2-1; provider: Google.

89.6% percentile inside its fair comparison set

81.3%Raw benchmark valueCI 80.5% - 82%

Terminal-Bench 4.0

TERMINAL-BENCH · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #23 · Source label: Gemini 3.8 Flash (high)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 19.1%
Percentile: 15.4%
Last updated: recent
Eligibility: headline eligible

15.4% percentile inside its fair comparison set

19.1%Raw benchmark valueCI 15.7% - 22.5%

SWE-bench Verified

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #23 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 80%
Percentile: 73.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: swebench; provider: Google.

73.2% percentile inside its fair comparison set

80%Raw benchmark valueCI 76.5% - 83.5%

LiveCodeBench

VALS-AI · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #3 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.5%
Percentile: 98.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: lcb; provider: Google.

98.4% percentile inside its fair comparison set

89.5%Raw benchmark valueCI 87.7% - 91.2%

Agentic coding

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #31 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 54.2%
Percentile: 53.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Agentic Coding. Tasks scored: 3.

53.8% percentile inside its fair comparison set

54.2%Raw benchmark value

Coding

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #54 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 72.5%
Percentile: 18.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Coding. Tasks scored: 2.

18.5% percentile inside its fair comparison set

72.5%Raw benchmark value

JavaScript

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #13 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 72.7%
Percentile: 87.7%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: javascript. Category: Agentic Coding.

87.7% percentile inside its fair comparison set

72.7%Raw benchmark value

TypeScript

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #35 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 40%
Percentile: 47.7%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: typescript. Category: Agentic Coding.

47.7% percentile inside its fair comparison set

40%Raw benchmark value

Python

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #51 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 50%
Percentile: 46.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: python. Category: Agentic Coding.

46.2% percentile inside its fair comparison set

50%Raw benchmark value

Coding generation

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #54 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 73.2%
Percentile: 21.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: code_generation. Category: Coding.

21.5% percentile inside its fair comparison set

73.2%Raw benchmark value

Coding completion

LB · Coding · Objective

It tells you whether the model can generate, repair, and reason over code under evaluator pressure rather than marketing examples.

Rank #55 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 71.7%
Percentile: 18.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: code_completion. Category: Coding.

18.5% percentile inside its fair comparison set

71.7%Raw benchmark value

Reasoning / math / science18 benchmarks81%

Humanity's Last Exam

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #33 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.8%
Percentile: 94%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

94% percentile inside its fair comparison set

47.8%Raw benchmark value

GPQA

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #3 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 95.3%
Percentile: 99.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

99.6% percentile inside its fair comparison set

95.3%Raw benchmark value

CritPt

AA · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #48 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 18.3%
Percentile: 89.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

89.7% percentile inside its fair comparison set

18.3%Raw benchmark value

Text Arena · Math

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #5 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: math. Source rank: #5. Votes: 1274. Organization: google. License: Proprietary.

98.9% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,501 - 1,534

Text Arena · Math · No Style Control

AR · Reasoning / math / science · Human

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #4 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,523
Percentile: 99.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: math. Source rank: #4. Votes: 1274. Organization: google. License: Proprietary.

99.2% percentile inside its fair comparison set

1,523Raw benchmark valueCI 1,506 - 1,540

ProofBench

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #27 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 48%
Percentile: 38.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: proof_bench; provider: Google.

38.1% percentile inside its fair comparison set

48%Raw benchmark valueCI 38.2% - 57.8%

GPQA Diamond

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #4 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 94.4%
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: gpqa; provider: Google.

97.6% percentile inside its fair comparison set

94.4%Raw benchmark valueCI 91.5% - 97.3%

MMLU Pro

VALS-AI · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #5 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 90.2%
Percentile: 96.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmlu_pro; provider: Google.

96.8% percentile inside its fair comparison set

90.2%Raw benchmark valueCI 89.6% - 90.8%

Mathematics

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #26 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 91.6%
Percentile: 61.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Mathematics. Tasks scored: 4.

61.5% percentile inside its fair comparison set

91.6%Raw benchmark value

Reasoning

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #18 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 89.3%
Percentile: 73.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Reasoning. Tasks scored: 4.

73.8% percentile inside its fair comparison set

89.3%Raw benchmark value

AMPS Hard

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #9 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 99%
Percentile: 98.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: AMPS_Hard. Category: Mathematics.

98.5% percentile inside its fair comparison set

99%Raw benchmark value

Integrals with game

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #32 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 80%
Percentile: 53.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: integrals_with_game. Category: Mathematics.

53.8% percentile inside its fair comparison set

80%Raw benchmark value

Math competition

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #48 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 95.1%
Percentile: 49.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: math_comp. Category: Mathematics.

49.2% percentile inside its fair comparison set

95.1%Raw benchmark value

Olympiad

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 92.2%
Percentile: 86.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: olympiad. Category: Mathematics.

86.2% percentile inside its fair comparison set

92.2%Raw benchmark value

Theory of mind

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #47 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76.9%
Percentile: 33.8%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: theory_of_mind. Category: Reasoning.

33.8% percentile inside its fair comparison set

76.9%Raw benchmark value

Zebra puzzle

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #23 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98.3%
Percentile: 67.7%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: zebra_puzzle. Category: Reasoning.

67.7% percentile inside its fair comparison set

98.3%Raw benchmark value

Spatial

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #17 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 100%
Percentile: 100%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: spatial. Category: Reasoning.

100% percentile inside its fair comparison set

100%Raw benchmark value

Logic with navigation

LB · Reasoning / math / science · Objective

It is one of the cleaner reads on deliberate reasoning strength rather than style or popularity.

Rank #12 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82%
Percentile: 86.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: logic_with_navigation. Category: Reasoning.

86.2% percentile inside its fair comparison set

82%Raw benchmark value

Professional reasoning35 benchmarks56%

PRBench Legal

SL · Professional reasoning · Rubric

Applied legal reasoning on professional-domain tasks.

Rank #13 · Source label: Gemini 3.8 Flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Scale Labs
Raw value: 48.9%
Percentile: 70.7%
Last updated: recent
Eligibility: headline eligible

Parsed from the public Scale Labs page for scale-prbench-legal. Reported model configuration: Gemini 3.8 Flash. Collapse policy: highest reported score per canonical model.

70.7% percentile inside its fair comparison set

48.9%Raw benchmark value

Text Arena · Expert

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #16 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,526
Percentile: 95.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: expert. Source rank: #16. Votes: 3109. Organization: google. License: Proprietary.

95.4% percentile inside its fair comparison set

1,526Raw benchmark valueCI 1,515 - 1,537

Text Arena · Industry Business And Management And Financial Operations

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #25 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,481
Percentile: 93.5%
Last updated: recent
Eligibility: headline eligible

93.5% percentile inside its fair comparison set

1,481Raw benchmark valueCI 1,472 - 1,490

Text Arena · Industry Entertainment And Sports And Media

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,471
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #10. Votes: 6903. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,471Raw benchmark valueCI 1,463 - 1,480

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #23 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,492
Percentile: 93.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_legal_and_government. Source rank: #23. Votes: 2385. Organization: google. License: Proprietary.

93.7% percentile inside its fair comparison set

1,492Raw benchmark valueCI 1,480 - 1,505

Text Arena · Industry Life And Physical And Social Science

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_life_and_physical_and_social_science. Source rank: #10. Votes: 4290. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,508 - 1,527

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #11 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 97.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_mathematical. Source rank: #11. Votes: 1506. Organization: google. License: Proprietary.

97.2% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,496 - 1,528

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,510
Percentile: 97.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_medicine_and_healthcare. Source rank: #10. Votes: 1840. Organization: google. License: Proprietary.

97.4% percentile inside its fair comparison set

1,510Raw benchmark valueCI 1,496 - 1,525

Text Arena · Industry Software And It Services

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #23 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,517
Percentile: 94.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_software_and_it_services. Source rank: #23. Votes: 10103. Organization: google. License: Proprietary.

94.1% percentile inside its fair comparison set

1,517Raw benchmark valueCI 1,510 - 1,523

Text Arena · Industry Writing And Literature And Language

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #9 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 97.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_writing_and_literature_and_language. Source rank: #9. Votes: 7274. Organization: google. License: Proprietary.

97.9% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,479 - 1,495

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena expert leaderboard.

Rank #11 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,527
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: expert. Source rank: #11. Votes: 3109. Organization: google. License: Proprietary.

96.9% percentile inside its fair comparison set

1,527Raw benchmark valueCI 1,516 - 1,538

Text Arena · Industry Business And Management And Financial Operations · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_business_and_management_and_financial_operations leaderboard.

Rank #12 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 97%
Last updated: recent
Eligibility: headline eligible

97% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,471 - 1,489

Text Arena · Industry Entertainment And Sports And Media · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_entertainment_and_sports_and_media leaderboard.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,474
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #10. Votes: 6903. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,474Raw benchmark valueCI 1,466 - 1,482

Text Arena · Industry Legal And Government · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_legal_and_government leaderboard.

Rank #12 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 96.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_legal_and_government. Source rank: #12. Votes: 2385. Organization: google. License: Proprietary.

96.8% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,486 - 1,511

Text Arena · Industry Life And Physical And Social Science · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_life_and_physical_and_social_science leaderboard.

Rank #6 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,521
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_life_and_physical_and_social_science. Source rank: #6. Votes: 4290. Organization: google. License: Proprietary.

98.7% percentile inside its fair comparison set

1,521Raw benchmark valueCI 1,511 - 1,530

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_mathematical leaderboard.

Rank #7 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,518
Percentile: 98.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_mathematical. Source rank: #7. Votes: 1506. Organization: google. License: Proprietary.

98.3% percentile inside its fair comparison set

1,518Raw benchmark valueCI 1,502 - 1,534

Text Arena · Industry Medicine And Healthcare · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_medicine_and_healthcare leaderboard.

Rank #5 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,509
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_medicine_and_healthcare. Source rank: #5. Votes: 1840. Organization: google. License: Proprietary.

98.8% percentile inside its fair comparison set

1,509Raw benchmark valueCI 1,495 - 1,524

Text Arena · Industry Software And It Services · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_software_and_it_services leaderboard.

Rank #14 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 96.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_software_and_it_services. Source rank: #14. Votes: 10103. Organization: google. License: Proprietary.

96.5% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,498 - 1,512

Text Arena · Industry Writing And Literature And Language · No Style Control

AR · Professional reasoning · Human

Observed user preference in Arena's Text Arena industry_writing_and_literature_and_language leaderboard.

Rank #11 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: industry_writing_and_literature_and_language. Source rank: #11. Votes: 7274. Organization: google. License: Proprietary.

97.3% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,482 - 1,498

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #15 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 55
Percentile: 65%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: vals_index; provider: Google.

65% percentile inside its fair comparison set

55Raw benchmark valueCI 53 - 57

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #26 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 38.9%
Percentile: 63.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_research; provider: Google.

63.2% percentile inside its fair comparison set

38.9%Raw benchmark valueCI 32.3% - 45.6%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

Completing legal work with documents, spreadsheets, presentations, and file-system tools.

Rank #14 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 10%
Percentile: 81.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: hlab; provider: Google.

81.2% percentile inside its fair comparison set

10%Raw benchmark valueCI 5.3% - 14.7%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #7 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87%
Percentile: 95.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: legal_bench; provider: Google.

95.6% percentile inside its fair comparison set

87%Raw benchmark valueCI 86.1% - 87.8%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #2 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 61.4%
Percentile: 98.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: fabv2; provider: Google.

98.6% percentile inside its fair comparison set

61.4%Raw benchmark valueCI 61.2% - 61.7%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #29 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 48.1%
Percentile: 70.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medcode; provider: Google.

70.5% percentile inside its fair comparison set

48.1%Raw benchmark valueCI 43.9% - 52.4%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #32 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 84.5%
Percentile: 67.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: medscribe; provider: Google.

67.7% percentile inside its fair comparison set

84.5%Raw benchmark valueCI 80.7% - 88.3%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #65 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 35.1%
Percentile: 21%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: sage; provider: Google.

21% percentile inside its fair comparison set

35.1%Raw benchmark valueCI 28.5% - 41.7%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #19 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.3%
Percentile: 60%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: public-benefits-bench; provider: Google.

60% percentile inside its fair comparison set

65.3%Raw benchmark valueCI 62.9% - 67.7%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #11 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 58%
Percentile: 69.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: skillsbench; provider: Google.

69.7% percentile inside its fair comparison set

58%Raw benchmark valueCI 49.3% - 66.7%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #36 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74.4%
Percentile: 72.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: tax_eval_v2; provider: Google.

72.9% percentile inside its fair comparison set

74.4%Raw benchmark valueCI 72.8% - 76.1%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #65 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 54%
Percentile: 1.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category: Data Analysis. Tasks scored: 3.

1.5% percentile inside its fair comparison set

54%Raw benchmark value

Overall

LB · Professional reasoning · Objective

Average objective performance across LiveBench's current public category mix.

Rank #34 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 75.8%
Percentile: 49.2%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Category averages included: 7.

49.2% percentile inside its fair comparison set

75.8%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #65 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 20.6%
Percentile: 1.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: consecutive_events. Category: Data Analysis.

1.5% percentile inside its fair comparison set

20.6%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #54 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45.3%
Percentile: 18.5%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: tablejoin. Category: Data Analysis.

18.5% percentile inside its fair comparison set

45.3%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #61 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.1%
Percentile: 20%
Last updated: stale
Eligibility: headline eligible

Derived from the official LiveBench website leaderboard table. Task: tablereformat. Category: Data Analysis.

20% percentile inside its fair comparison set

96.1%Raw benchmark value

Long context1 benchmark92.1%

Long Context Reasoning

AA · Long context · Objective

It checks whether long-context claims survive contact with retrieval, memory, or long-document tasks.

Rank #39 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 81.3%
Percentile: 92.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

92.1% percentile inside its fair comparison set

81.3%Raw benchmark value

Vision understanding14 benchmarks95.1%

MMMU-Pro

AA · Vision understanding · Objective

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #9 · Source label: Gemini 3.8 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 85.6%
Percentile: 96.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

96.2% percentile inside its fair comparison set

85.6%Raw benchmark value

Vision Arena

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #11 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,290
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: overall. Source rank: #11. Votes: 3086. Organization: google. License: Proprietary.

92.8% percentile inside its fair comparison set

1,290Raw benchmark valueCI 1,279 - 1,302

Vision Arena · Creative Writing Vision

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #32 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,255
Percentile: 62.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: creative_writing_vision. Source rank: #37. Votes: 284. Organization: google. License: Proprietary.

62.2% percentile inside its fair comparison set

1,255Raw benchmark valueCI 1,219 - 1,292

Vision Arena · Diagram

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #2 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,341
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: diagram. Source rank: #2. Votes: 793. Organization: google. License: Proprietary.

99% percentile inside its fair comparison set

1,341Raw benchmark valueCI 1,319 - 1,363

Vision Arena · English

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,291
Percentile: 94.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: english. Source rank: #8. Votes: 1010. Organization: google. License: Proprietary.

94.9% percentile inside its fair comparison set

1,291Raw benchmark valueCI 1,271 - 1,310

Vision Arena · Homework

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #7 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,334
Percentile: 93.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: homework. Source rank: #7. Votes: 418. Organization: google. License: Proprietary.

93.8% percentile inside its fair comparison set

1,334Raw benchmark valueCI 1,305 - 1,362

Vision Arena · Ocr

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #3 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,315
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: ocr. Source rank: #3. Votes: 2081. Organization: google. License: Proprietary.

98% percentile inside its fair comparison set

1,315Raw benchmark valueCI 1,301 - 1,329

Vision Arena · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #5 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,316
Percentile: 97.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: overall. Source rank: #5. Votes: 3086. Organization: google. License: Proprietary.

97.1% percentile inside its fair comparison set

1,316Raw benchmark valueCI 1,304 - 1,327

Vision Arena · Creative Writing Vision · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #25 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,280
Percentile: 70.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: creative_writing_vision. Source rank: #28. Votes: 284. Organization: google. License: Proprietary.

70.7% percentile inside its fair comparison set

1,280Raw benchmark valueCI 1,245 - 1,316

Vision Arena · Diagram · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #2 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,353
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: diagram. Source rank: #2. Votes: 793. Organization: google. License: Proprietary.

99% percentile inside its fair comparison set

1,353Raw benchmark valueCI 1,331 - 1,375

Vision Arena · English · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #6 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,318
Percentile: 96.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: english. Source rank: #6. Votes: 1010. Organization: google. License: Proprietary.

96.4% percentile inside its fair comparison set

1,318Raw benchmark valueCI 1,299 - 1,338

Vision Arena · Homework · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #3 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,347
Percentile: 97.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: homework. Source rank: #3. Votes: 418. Organization: google. License: Proprietary.

97.9% percentile inside its fair comparison set

1,347Raw benchmark valueCI 1,319 - 1,376

Vision Arena · Ocr · No Style Control

AR · Vision understanding · Human

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #2 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,333
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: ocr. Source rank: #2. Votes: 2081. Organization: google. License: Proprietary.

99% percentile inside its fair comparison set

1,333Raw benchmark valueCI 1,320 - 1,347

MMMU Pro

VALS-AI · Vision understanding · Objective

It is useful when the model must read charts, UI, screenshots, or visual scenes rather than text alone.

Rank #4 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89.1%
Percentile: 96.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mmmu; provider: Google.

96.4% percentile inside its fair comparison set

89.1%Raw benchmark valueCI 87.6% - 90.5%

Document understanding1 benchmark52.3%

MortgageTax

VALS-AI · Document understanding · Objective

It matters when the job is reading PDFs, tables, forms, or mixed-layout documents rather than plain chat.

Rank #42 · Source label: google/gemini-3.8-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.3%
Percentile: 52.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Vals AI BenchmarkView overall scores. Vals slug: mortgage_tax; provider: Google.

52.3% percentile inside its fair comparison set

65.3%Raw benchmark valueCI 63.5% - 67.2%

Multilingual18 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #14 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,536
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: chinese. Source rank: #14. Votes: 2061. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,536Raw benchmark valueCI 1,522 - 1,550

Text Arena · French

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #18 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 93.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: french. Source rank: #18. Votes: 789. Organization: google. License: Proprietary.

93.4% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,483 - 1,528

Text Arena · German

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #37 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,472
Percentile: 86.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: german. Source rank: #40. Votes: 398. Organization: google. License: Proprietary.

86.8% percentile inside its fair comparison set

1,472Raw benchmark valueCI 1,443 - 1,500

Text Arena · Japanese

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #7 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: japanese. Source rank: #7. Votes: 462. Organization: google. License: Proprietary.

97.5% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,473 - 1,533

Text Arena · Korean

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #17 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,456
Percentile: 93.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: korean. Source rank: #17. Votes: 487. Organization: google. License: Proprietary.

93.4% percentile inside its fair comparison set

1,456Raw benchmark valueCI 1,427 - 1,484

Text Arena · Non English

AR · Multilingual · Human

Observed user preference in Arena's Text Arena non_english leaderboard.

Rank #11 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: non_english. Source rank: #11. Votes: 15930. Organization: google. License: Proprietary.

97.3% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,478 - 1,490

Text Arena · Polish

AR · Multilingual · Human

Observed user preference in Arena's Text Arena polish leaderboard.

Rank #10 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,501
Percentile: 95.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: polish. Source rank: #10. Votes: 364. Organization: google. License: Proprietary.

95.5% percentile inside its fair comparison set

1,501Raw benchmark valueCI 1,471 - 1,532

Text Arena · Russian

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #5 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,510
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: russian. Source rank: #5. Votes: 3357. Organization: google. License: Proprietary.

98.8% percentile inside its fair comparison set

1,510Raw benchmark valueCI 1,500 - 1,521

Text Arena · Spanish

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #19 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,476
Percentile: 93.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: spanish. Source rank: #19. Votes: 848. Organization: google. License: Proprietary.

93.1% percentile inside its fair comparison set

1,476Raw benchmark valueCI 1,456 - 1,497

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena chinese leaderboard.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,551
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: chinese. Source rank: #8. Votes: 2061. Organization: google. License: Proprietary.

98% percentile inside its fair comparison set

1,551Raw benchmark valueCI 1,537 - 1,564

Text Arena · French · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena french leaderboard.

Rank #11 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 96.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: french. Source rank: #11. Votes: 789. Organization: google. License: Proprietary.

96.1% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,478 - 1,523

Text Arena · German · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena german leaderboard.

Rank #21 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: german. Source rank: #22. Votes: 398. Organization: google. License: Proprietary.

92.6% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,450 - 1,507

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena japanese leaderboard.

Rank #7 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: japanese. Source rank: #7. Votes: 462. Organization: google. License: Proprietary.

97.5% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,473 - 1,533

Text Arena · Korean · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena korean leaderboard.

Rank #8 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,468
Percentile: 97.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: korean. Source rank: #8. Votes: 487. Organization: google. License: Proprietary.

97.1% percentile inside its fair comparison set

1,468Raw benchmark valueCI 1,440 - 1,497

Text Arena · Non English · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena non_english leaderboard.

Rank #7 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 98.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: non_english. Source rank: #7. Votes: 15930. Organization: google. License: Proprietary.

98.4% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,482 - 1,494

Text Arena · Polish · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena polish leaderboard.

Rank #6 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,505
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: polish. Source rank: #6. Votes: 364. Organization: google. License: Proprietary.

97.5% percentile inside its fair comparison set

1,505Raw benchmark valueCI 1,475 - 1,535

Text Arena · Russian · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena russian leaderboard.

Rank #4 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,510
Percentile: 99.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: russian. Source rank: #4. Votes: 3357. Organization: google. License: Proprietary.

99.1% percentile inside its fair comparison set

1,510Raw benchmark valueCI 1,500 - 1,521

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

Observed user preference in Arena's Text Arena spanish leaderboard.

Rank #12 · Source label: gemini-3.8-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 95.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.8-flash-high`. Category: spanish. Source rank: #12. Votes: 848. Organization: google. License: Proprietary.

95.8% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,464 - 1,505

Source links and registry checks

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

official

LiveBench

Oct 3, 2026

source →

official

Scale Labs

Oct 3, 2026

source →

official

Scale Labs

Oct 3, 2026

source →

official

Terminal-Bench

Oct 3, 2026

source →

gemini-3.8-flash-high

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

gemini-3.8-flash-high

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks