Model profile · Google

gemini-3.7-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: 48.6%
Verified coverage: 48.6%
Spread: 100%
Last verified: Oct 3, 2026

66%capability fit

textcodevisiondocument4 aliases42 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 benchmarks89.6%

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 #58 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 39
Percentile: 89.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

89.7% percentile inside its fair comparison set

39Raw 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 #27 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 55.3%
Percentile: 94.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

94.3% percentile inside its fair comparison set

55.3%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 #143 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 35.5%
Percentile: 68.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

68.7% percentile inside its fair comparison set

35.5%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 #213 · Source label: Gemini 3.7 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 #220 · Source label: Gemini 3.7 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 #8 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 302.6 tokens/s
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

97.3% percentile inside its fair comparison set

302.6 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 #192 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 11.67s
Percentile: 27.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

27.7% percentile inside its fair comparison set

11.67sRaw 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 #97 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 11.67s
Percentile: 63.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

63.4% percentile inside its fair comparison set

11.67sRaw 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 #17 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: overall. Source rank: #17. Votes: 21539. Organization: google. License: Proprietary.

95.7% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,483 - 1,493

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 #5 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,493
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: creative_writing. Source rank: #5. Votes: 4776. Organization: google. License: Proprietary.

98.9% percentile inside its fair comparison set

1,493Raw benchmark valueCI 1,484 - 1,503

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 #29 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: english. Source rank: #29. Votes: 8659. Organization: google. License: Proprietary.

92.6% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,478 - 1,493

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 #15 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: exclude_ties. Source rank: #15. Votes: 16101. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,496 - 1,510

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 #19 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,508
Percentile: 95.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: hard_prompts. Source rank: #19. Votes: 14188. Organization: google. License: Proprietary.

95.2% percentile inside its fair comparison set

1,508Raw benchmark valueCI 1,502 - 1,514

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 #37 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 90.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: hard_prompts_english. Source rank: #37. Votes: 5704. Organization: google. License: Proprietary.

90.4% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,491 - 1,508

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 #17 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: instruction_following. Source rank: #17. Votes: 7768. Organization: google. License: Proprietary.

95.7% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,477 - 1,492

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 #13 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: longer_query. Source rank: #13. Votes: 10222. Organization: google. License: Proprietary.

96.6% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,493 - 1,507

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 #19 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,493
Percentile: 95.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: multi_turn. Source rank: #19. Votes: 3282. Organization: google. License: Proprietary.

95.2% percentile inside its fair comparison set

1,493Raw benchmark valueCI 1,482 - 1,504

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 #13 · Source label: gemini-3.7-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-3.7-flash-high`. Category: overall. Source rank: #13. Votes: 21539. Organization: google. License: Proprietary.

96.8% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,482 - 1,492

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 #7 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 98.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: creative_writing. Source rank: #7. Votes: 4776. Organization: google. License: Proprietary.

98.4% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,481 - 1,500

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 #17 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: english. Source rank: #17. Votes: 8659. Organization: google. License: Proprietary.

95.7% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,477 - 1,491

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 #13 · Source label: gemini-3.7-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-3.7-flash-high`. Category: exclude_ties. Source rank: #13. Votes: 16101. Organization: google. License: Proprietary.

96.8% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,492 - 1,505

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 #15 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: hard_prompts. Source rank: #15. Votes: 14188. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,490 - 1,502

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 #22 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: hard_prompts_english. Source rank: #22. Votes: 5704. Organization: google. License: Proprietary.

94.4% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,480 - 1,497

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 #14 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 96.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: instruction_following. Source rank: #14. Votes: 7768. Organization: google. License: Proprietary.

96.5% percentile inside its fair comparison set

1,483Raw benchmark valueCI 1,476 - 1,491

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 #14 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,493
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: longer_query. Source rank: #14. Votes: 10222. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,493Raw benchmark valueCI 1,486 - 1,500

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 #13 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 96.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: multi_turn. Source rank: #13. Votes: 3282. Organization: google. License: Proprietary.

96.8% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,479 - 1,501

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 #2 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 79.9%
Percentile: 98.5%
Last updated: stale
Eligibility: headline eligible

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

98.5% percentile inside its fair comparison set

79.9%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 #13 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 85.5%
Percentile: 81.5%
Last updated: stale
Eligibility: headline eligible

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

81.5% percentile inside its fair comparison set

85.5%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 #6 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.1%
Percentile: 92.3%
Last updated: stale
Eligibility: headline eligible

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

92.3% percentile inside its fair comparison set

78.1%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 #3 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74.6%
Percentile: 96.9%
Last updated: stale
Eligibility: headline eligible

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

96.9% percentile inside its fair comparison set

74.6%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 #2 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82.3%
Percentile: 98.5%
Last updated: stale
Eligibility: headline eligible

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

98.5% percentile inside its fair comparison set

82.3%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 #3 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84.8%
Percentile: 96.9%
Last updated: stale
Eligibility: headline eligible

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

96.9% percentile inside its fair comparison set

84.8%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 #12 · Source label: gemini-3.7-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 #25 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 66.4%
Percentile: 63.1%
Last updated: stale
Eligibility: headline eligible

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

63.1% percentile inside its fair comparison set

66.4%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 #4 · Source label: gemini-3.7-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

Coding21 benchmarks61.4%

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 #25 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 57.2%
Percentile: 87.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

87.9% percentile inside its fair comparison set

57.2%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 #41 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,518
Percentile: 89.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: coding. Source rank: #41. Votes: 6041. Organization: google. License: Proprietary.

89.2% percentile inside its fair comparison set

1,518Raw benchmark valueCI 1,510 - 1,526

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 #24 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 93.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: coding. Source rank: #24. Votes: 6041. Organization: google. License: Proprietary.

93.8% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,490 - 1,506

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 #32 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 70.4%
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

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

66.7% percentile inside its fair comparison set

70.4%Raw benchmark valueCI 60.9% - 79.9%

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 #26 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,592
Percentile: 80.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: overall. Source rank: #27. Votes: 9624. Organization: google. License: Proprietary.

80.3% percentile inside its fair comparison set

1,592Raw benchmark valueCI 1,584 - 1,599

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 #22 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,604
Percentile: 83.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: webdev-html. Source rank: #23. Votes: 1363. Organization: google. License: Proprietary.

83.2% percentile inside its fair comparison set

1,604Raw benchmark valueCI 1,586 - 1,622

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 #27 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,589
Percentile: 77%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: webdev-react. Source rank: #28. Votes: 6433. Organization: google. License: Proprietary.

77% percentile inside its fair comparison set

1,589Raw benchmark valueCI 1,580 - 1,598

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 #34 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 34.8%
Percentile: 51.5%
Last updated: recent
Eligibility: headline eligible

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

51.5% percentile inside its fair comparison set

34.8%Raw benchmark valueCI 26.5% - 43.1%

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 #13 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 67.8%
Percentile: 67.6%
Last updated: recent
Eligibility: headline eligible

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

67.6% percentile inside its fair comparison set

67.8%Raw benchmark valueCI 60.8% - 74.9%

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 #33 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0%
Percentile: 51.7%
Last updated: recent
Eligibility: headline eligible

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

51.7% percentile inside its fair comparison set

0%Raw benchmark valueCI 0% - 0%

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 #14 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 77.5%
Percentile: 80.6%
Last updated: recent
Eligibility: headline eligible

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

80.6% percentile inside its fair comparison set

77.5%Raw benchmark valueCI 76.3% - 78.8%

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 #22 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 80.8%
Percentile: 74.4%
Last updated: recent
Eligibility: headline eligible

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

74.4% percentile inside its fair comparison set

80.8%Raw benchmark valueCI 77.3% - 84.3%

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 #5 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.7%
Percentile: 96.8%
Last updated: recent
Eligibility: headline eligible

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

96.8% percentile inside its fair comparison set

88.7%Raw benchmark valueCI 86.8% - 90.5%

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 #27 · Source label: Gemini 3.7 Flash (high)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 11.2%
Percentile: 0%
Last updated: aging
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 3.7 Flash. Agent URL: https://github.com/SWE-agent/mini-swe-agent. Reported stderr: 1.250 percentage points.

0% percentile inside its fair comparison set

11.2%Raw benchmark valueCI 8.8% - 13.7%

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 #19 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 58.3%
Percentile: 72.3%
Last updated: stale
Eligibility: headline eligible

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

72.3% percentile inside its fair comparison set

58.3%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 #29 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.9%
Percentile: 56.9%
Last updated: stale
Eligibility: headline eligible

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

56.9% percentile inside its fair comparison set

78.9%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 #24 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68.2%
Percentile: 78.5%
Last updated: stale
Eligibility: headline eligible

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

78.5% percentile inside its fair comparison set

68.2%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 #21 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 46.7%
Percentile: 72.3%
Last updated: stale
Eligibility: headline eligible

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

72.3% percentile inside its fair comparison set

46.7%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 #19 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 60%
Percentile: 80%
Last updated: stale
Eligibility: headline eligible

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

80% percentile inside its fair comparison set

60%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 #13 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 81.7%
Percentile: 83.1%
Last updated: stale
Eligibility: headline eligible

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

83.1% percentile inside its fair comparison set

81.7%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 #47 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76.1%
Percentile: 40%
Last updated: stale
Eligibility: headline eligible

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

40% percentile inside its fair comparison set

76.1%Raw benchmark value

Reasoning / math / science18 benchmarks82.1%

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 #32 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.9%
Percentile: 94.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

94.1% percentile inside its fair comparison set

47.9%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 #6 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 94.5%
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

99% percentile inside its fair comparison set

94.5%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 #69 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 14.3%
Percentile: 85.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

85.1% percentile inside its fair comparison set

14.3%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 #12 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: math. Source rank: #12. Votes: 1097. Organization: google. License: Proprietary.

96.9% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,485 - 1,521

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 #10 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,507
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: math. Source rank: #10. Votes: 1097. Organization: google. License: Proprietary.

97.5% percentile inside its fair comparison set

1,507Raw benchmark valueCI 1,489 - 1,525

ProofBench

VALS-AI · Reasoning / math / science · Objective

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

Rank #19 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 58%
Percentile: 57.1%
Last updated: recent
Eligibility: headline eligible

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

57.1% percentile inside its fair comparison set

58%Raw benchmark valueCI 48.3% - 67.7%

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 #5 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 93.9%
Percentile: 96.8%
Last updated: recent
Eligibility: headline eligible

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

96.8% percentile inside its fair comparison set

93.9%Raw benchmark valueCI 91% - 96.9%

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 #6 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 90.1%
Percentile: 96%
Last updated: recent
Eligibility: headline eligible

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

96% percentile inside its fair comparison set

90.1%Raw benchmark valueCI 89.5% - 90.7%

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #20 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 93.5%
Percentile: 70.8%
Last updated: stale
Eligibility: headline eligible

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

70.8% percentile inside its fair comparison set

93.5%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 #25 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 87.8%
Percentile: 63.1%
Last updated: stale
Eligibility: headline eligible

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

63.1% percentile inside its fair comparison set

87.8%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 #32 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 83.1%
Last updated: stale
Eligibility: headline eligible

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

83.1% percentile inside its fair comparison set

98%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 #25 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 88%
Percentile: 64.6%
Last updated: stale
Eligibility: headline eligible

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

64.6% percentile inside its fair comparison set

88%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 #30 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.1%
Percentile: 66.2%
Last updated: stale
Eligibility: headline eligible

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

66.2% percentile inside its fair comparison set

96.1%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 #15 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 91.8%
Percentile: 78.5%
Last updated: stale
Eligibility: headline eligible

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

78.5% percentile inside its fair comparison set

91.8%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 #22 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82.7%
Percentile: 72.3%
Last updated: stale
Eligibility: headline eligible

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

72.3% percentile inside its fair comparison set

82.7%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 #37 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 94.5%
Percentile: 44.6%
Last updated: stale
Eligibility: headline eligible

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

44.6% percentile inside its fair comparison set

94.5%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 #14 · Source label: gemini-3.7-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 #32 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74%
Percentile: 58.5%
Last updated: stale
Eligibility: headline eligible

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

58.5% percentile inside its fair comparison set

74%Raw benchmark value

Professional reasoning33 benchmarks54.4%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #27 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,511
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: expert. Source rank: #28. Votes: 2521. Organization: google. License: Proprietary.

92% percentile inside its fair comparison set

1,511Raw benchmark valueCI 1,499 - 1,523

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 #22 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 94.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_business_and_management_and_financial_operations. Source rank: #23. Votes: 3963. Organization: google. License: Proprietary.

94.3% percentile inside its fair comparison set

1,483Raw benchmark valueCI 1,473 - 1,493

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 #6 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #6. Votes: 5743. Organization: google. License: Proprietary.

98.7% percentile inside its fair comparison set

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

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #24 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 93.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_legal_and_government. Source rank: #24. Votes: 1820. Organization: google. License: Proprietary.

93.4% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,477 - 1,506

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 #14 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,513
Percentile: 96.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_life_and_physical_and_social_science. Source rank: #14. Votes: 3613. Organization: google. License: Proprietary.

96.5% percentile inside its fair comparison set

1,513Raw benchmark valueCI 1,503 - 1,523

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #23 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 93.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_mathematical. Source rank: #24. Votes: 1333. Organization: google. License: Proprietary.

93.8% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,479 - 1,512

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #26 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_medicine_and_healthcare. Source rank: #26. Votes: 1517. Organization: google. License: Proprietary.

92.8% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,480 - 1,512

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 #30 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 92.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_software_and_it_services. Source rank: #30. Votes: 8363. Organization: google. License: Proprietary.

92.3% percentile inside its fair comparison set

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

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 #6 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_writing_and_literature_and_language. Source rank: #6. Votes: 5961. Organization: google. License: Proprietary.

98.7% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,487 - 1,504

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #23 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,507
Percentile: 93.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: expert. Source rank: #23. Votes: 2521. Organization: google. License: Proprietary.

93.3% percentile inside its fair comparison set

1,507Raw benchmark valueCI 1,495 - 1,519

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 #14 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,478
Percentile: 96.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_business_and_management_and_financial_operations. Source rank: #14. Votes: 3963. Organization: google. License: Proprietary.

96.5% percentile inside its fair comparison set

1,478Raw benchmark valueCI 1,469 - 1,488

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 #8 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #8. Votes: 5743. Organization: google. License: Proprietary.

98.1% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,470 - 1,487

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 #14 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_legal_and_government. Source rank: #14. Votes: 1820. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,479 - 1,508

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 #10 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,511
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_life_and_physical_and_social_science. Source rank: #10. Votes: 3613. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,511Raw benchmark valueCI 1,501 - 1,521

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #14 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_mathematical. Source rank: #14. Votes: 1333. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,482 - 1,515

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 #17 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 95.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_medicine_and_healthcare. Source rank: #17. Votes: 1517. Organization: google. License: Proprietary.

95.4% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,473 - 1,504

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 #19 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 95.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_software_and_it_services. Source rank: #19. Votes: 8363. Organization: google. License: Proprietary.

95.2% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,492 - 1,506

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 #7 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 98.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_writing_and_literature_and_language. Source rank: #7. Votes: 5961. Organization: google. License: Proprietary.

98.4% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,485 - 1,503

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #23 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 51
Percentile: 45%
Last updated: recent
Eligibility: headline eligible

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

45% percentile inside its fair comparison set

51Raw benchmark valueCI 49 - 53

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #35 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 34.6%
Percentile: 50%
Last updated: recent
Eligibility: headline eligible

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

50% percentile inside its fair comparison set

34.6%Raw benchmark valueCI 28.1% - 41.1%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #18 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 8.8%
Percentile: 75.4%
Last updated: recent
Eligibility: headline eligible

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

75.4% percentile inside its fair comparison set

8.8%Raw benchmark valueCI 4.5% - 13%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #5 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.3%
Percentile: 97%
Last updated: recent
Eligibility: headline eligible

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

97% percentile inside its fair comparison set

87.3%Raw benchmark valueCI 86.4% - 88.1%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #5 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 59%
Percentile: 94.2%
Last updated: recent
Eligibility: headline eligible

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

94.2% percentile inside its fair comparison set

59%Raw benchmark valueCI 58.5% - 59.6%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #9 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 53.4%
Percentile: 91.6%
Last updated: recent
Eligibility: headline eligible

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

91.6% percentile inside its fair comparison set

53.4%Raw benchmark valueCI 49.2% - 57.5%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #37 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.9%
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

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

62.5% percentile inside its fair comparison set

83.9%Raw benchmark valueCI 80% - 87.9%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #23 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 49.2%
Percentile: 72.8%
Last updated: recent
Eligibility: headline eligible

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

72.8% percentile inside its fair comparison set

49.2%Raw benchmark valueCI 42.6% - 55.9%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #3 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.9%
Percentile: 93.9%
Last updated: recent
Eligibility: headline eligible

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

93.9% percentile inside its fair comparison set

65.9%Raw benchmark valueCI 57% - 74.8%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #31 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74.7%
Percentile: 76.7%
Last updated: recent
Eligibility: headline eligible

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

76.7% percentile inside its fair comparison set

74.7%Raw benchmark valueCI 73.1% - 76.4%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #55 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68%
Percentile: 16.9%
Last updated: stale
Eligibility: headline eligible

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

16.9% percentile inside its fair comparison set

68%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #16 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.8%
Percentile: 76.9%
Last updated: stale
Eligibility: headline eligible

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

76.9% percentile inside its fair comparison set

78.8%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #54 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 60.4%
Percentile: 18.5%
Last updated: stale
Eligibility: headline eligible

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

18.5% percentile inside its fair comparison set

60.4%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #53 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45.5%
Percentile: 20%
Last updated: stale
Eligibility: headline eligible

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

20% percentile inside its fair comparison set

45.5%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #45 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 61.5%
Last updated: stale
Eligibility: headline eligible

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

61.5% percentile inside its fair comparison set

98%Raw benchmark value

Long context1 benchmark92.5%

Long Context Reasoning

AA · Long context · Objective

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

Rank #36 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 81.7%
Percentile: 92.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

92.5% percentile inside its fair comparison set

81.7%Raw benchmark value

Vision understanding14 benchmarks95.8%

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 #10 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 85.5%
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

95.7% percentile inside its fair comparison set

85.5%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 #6 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,296
Percentile: 96.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: overall. Source rank: #6. Votes: 3814. Organization: google. License: Proprietary.

96.4% percentile inside its fair comparison set

1,296Raw benchmark valueCI 1,286 - 1,306

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 #17 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,283
Percentile: 80.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: creative_writing_vision. Source rank: #17. Votes: 364. Organization: google. License: Proprietary.

80.5% percentile inside its fair comparison set

1,283Raw benchmark valueCI 1,250 - 1,316

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 #12 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,321
Percentile: 88.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: diagram. Source rank: #12. Votes: 973. Organization: google. License: Proprietary.

88.9% percentile inside its fair comparison set

1,321Raw benchmark valueCI 1,301 - 1,341

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 #12 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,283
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: english. Source rank: #12. Votes: 1317. Organization: google. License: Proprietary.

92% percentile inside its fair comparison set

1,283Raw benchmark valueCI 1,265 - 1,300

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 #17 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,320
Percentile: 83.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: homework. Source rank: #18. Votes: 442. Organization: google. License: Proprietary.

83.3% percentile inside its fair comparison set

1,320Raw benchmark valueCI 1,292 - 1,347

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 #7 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,311
Percentile: 94%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: ocr. Source rank: #7. Votes: 2612. Organization: google. License: Proprietary.

94% percentile inside its fair comparison set

1,311Raw benchmark valueCI 1,300 - 1,323

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 #7 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,315
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: overall. Source rank: #7. Votes: 3814. Organization: google. License: Proprietary.

95.7% percentile inside its fair comparison set

1,315Raw benchmark valueCI 1,305 - 1,325

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 #15 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,304
Percentile: 82.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: creative_writing_vision. Source rank: #15. Votes: 364. Organization: google. License: Proprietary.

82.9% percentile inside its fair comparison set

1,304Raw benchmark valueCI 1,272 - 1,337

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 #10 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,329
Percentile: 90.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: diagram. Source rank: #10. Votes: 973. Organization: google. License: Proprietary.

90.9% percentile inside its fair comparison set

1,329Raw benchmark valueCI 1,310 - 1,349

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 #12 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,303
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: english. Source rank: #12. Votes: 1317. Organization: google. License: Proprietary.

92% percentile inside its fair comparison set

1,303Raw benchmark valueCI 1,286 - 1,321

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 #16 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,330
Percentile: 84.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: homework. Source rank: #17. Votes: 442. Organization: google. License: Proprietary.

84.4% percentile inside its fair comparison set

1,330Raw benchmark valueCI 1,303 - 1,358

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 #8 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,325
Percentile: 93%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: ocr. Source rank: #8. Votes: 2612. Organization: google. License: Proprietary.

93% percentile inside its fair comparison set

1,325Raw benchmark valueCI 1,313 - 1,337

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 #5 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89%
Percentile: 95.2%
Last updated: recent
Eligibility: headline eligible

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

95.2% percentile inside its fair comparison set

89%Raw benchmark valueCI 87.5% - 90.4%

Document understanding1 benchmark65.1%

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 #31 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 66.7%
Percentile: 65.1%
Last updated: recent
Eligibility: headline eligible

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

65.1% percentile inside its fair comparison set

66.7%Raw benchmark valueCI 64.8% - 68.5%

Multilingual20 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #8 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,546
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: chinese. Source rank: #8. Votes: 1681. Organization: google. License: Proprietary.

98% percentile inside its fair comparison set

1,546Raw benchmark valueCI 1,532 - 1,561

Text Arena · French

AR · Multilingual · Human

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

Rank #8 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,511
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: french. Source rank: #8. Votes: 614. Organization: google. License: Proprietary.

97.3% percentile inside its fair comparison set

1,511Raw benchmark valueCI 1,486 - 1,536

Text Arena · German

AR · Multilingual · Human

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

Rank #21 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: german. Source rank: #21. Votes: 313. Organization: google. License: Proprietary.

92.6% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,454 - 1,520

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #5 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 98.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: japanese. Source rank: #5. Votes: 340. Organization: google. License: Proprietary.

98.4% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,471 - 1,538

Text Arena · Korean

AR · Multilingual · Human

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

Rank #7 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: korean. Source rank: #7. Votes: 404. Organization: google. License: Proprietary.

97.5% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,449 - 1,511

Text Arena · Non English

AR · Multilingual · Human

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

Rank #10 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: non_english. Source rank: #10. Votes: 12873. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,478 - 1,491

Text Arena · Polish

AR · Multilingual · Human

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

Rank #4 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: polish. Source rank: #4. Votes: 318. Organization: google. License: Proprietary.

98.5% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,472 - 1,539

Text Arena · Russian

AR · Multilingual · Human

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

Rank #2 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,519
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: russian. Source rank: #2. Votes: 2610. Organization: google. License: Proprietary.

99.7% percentile inside its fair comparison set

1,519Raw benchmark valueCI 1,507 - 1,531

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #5 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: spanish. Source rank: #5. Votes: 639. Organization: google. License: Proprietary.

98.5% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,471 - 1,518

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #7 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,551
Percentile: 98.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: chinese. Source rank: #7. Votes: 1681. Organization: google. License: Proprietary.

98.3% percentile inside its fair comparison set

1,551Raw benchmark valueCI 1,536 - 1,566

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #8 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: french. Source rank: #8. Votes: 614. Organization: google. License: Proprietary.

97.3% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,479 - 1,529

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #13 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 95.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: german. Source rank: #13. Votes: 313. Organization: google. License: Proprietary.

95.6% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,458 - 1,524

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #6 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 97.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: japanese. Source rank: #6. Votes: 340. Organization: google. License: Proprietary.

97.9% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,470 - 1,537

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #6 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: korean. Source rank: #6. Votes: 404. Organization: google. License: Proprietary.

98% percentile inside its fair comparison set

1,483Raw benchmark valueCI 1,452 - 1,514

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #9 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 97.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: non_english. Source rank: #9. Votes: 12873. Organization: google. License: Proprietary.

97.9% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,478 - 1,491

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #5 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,507
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: polish. Source rank: #5. Votes: 318. Organization: google. License: Proprietary.

98% percentile inside its fair comparison set

1,507Raw benchmark valueCI 1,474 - 1,540

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #3 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,516
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: russian. Source rank: #3. Votes: 2610. Organization: google. License: Proprietary.

99.4% percentile inside its fair comparison set

1,516Raw benchmark valueCI 1,504 - 1,528

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #8 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: spanish. Source rank: #8. Votes: 639. Organization: google. License: Proprietary.

97.3% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,475 - 1,523

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #1 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,377
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: chinese. Source rank: #1. Votes: 212. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,377Raw benchmark valueCI 1,336 - 1,418

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #2 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: chinese. Source rank: #2. Votes: 212. Organization: google. License: Proprietary.

99% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,361 - 1,442

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

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

official

LiveBench

Oct 3, 2026

source →

official

Terminal-Bench

Oct 3, 2026

source →

Model profile · Google

gemini-3.7-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: 48.6%
Verified coverage: 48.6%
Spread: 100%
Last verified: Oct 3, 2026

66%capability fit

textcodevisiondocument4 aliases42 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 benchmarks89.6%

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 #58 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 39
Percentile: 89.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

89.7% percentile inside its fair comparison set

39Raw 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 #27 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 55.3%
Percentile: 94.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

94.3% percentile inside its fair comparison set

55.3%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 #143 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 35.5%
Percentile: 68.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

68.7% percentile inside its fair comparison set

35.5%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 #213 · Source label: Gemini 3.7 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 #220 · Source label: Gemini 3.7 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 #8 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 302.6 tokens/s
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianOutputTokensPerSecond`.

97.3% percentile inside its fair comparison set

302.6 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 #192 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 11.67s
Percentile: 27.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstTokenSeconds`.

27.7% percentile inside its fair comparison set

11.67sRaw 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 #97 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 11.67s
Percentile: 63.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `medianTimeToFirstAnswerTokenSeconds`.

63.4% percentile inside its fair comparison set

11.67sRaw 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 #17 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: overall. Source rank: #17. Votes: 21539. Organization: google. License: Proprietary.

95.7% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,483 - 1,493

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 #5 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,493
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: creative_writing. Source rank: #5. Votes: 4776. Organization: google. License: Proprietary.

98.9% percentile inside its fair comparison set

1,493Raw benchmark valueCI 1,484 - 1,503

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 #29 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: english. Source rank: #29. Votes: 8659. Organization: google. License: Proprietary.

92.6% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,478 - 1,493

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 #15 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: exclude_ties. Source rank: #15. Votes: 16101. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,496 - 1,510

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 #19 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,508
Percentile: 95.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: hard_prompts. Source rank: #19. Votes: 14188. Organization: google. License: Proprietary.

95.2% percentile inside its fair comparison set

1,508Raw benchmark valueCI 1,502 - 1,514

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 #37 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 90.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: hard_prompts_english. Source rank: #37. Votes: 5704. Organization: google. License: Proprietary.

90.4% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,491 - 1,508

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 #17 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: instruction_following. Source rank: #17. Votes: 7768. Organization: google. License: Proprietary.

95.7% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,477 - 1,492

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 #13 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,500
Percentile: 96.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: longer_query. Source rank: #13. Votes: 10222. Organization: google. License: Proprietary.

96.6% percentile inside its fair comparison set

1,500Raw benchmark valueCI 1,493 - 1,507

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 #19 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,493
Percentile: 95.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: multi_turn. Source rank: #19. Votes: 3282. Organization: google. License: Proprietary.

95.2% percentile inside its fair comparison set

1,493Raw benchmark valueCI 1,482 - 1,504

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 #13 · Source label: gemini-3.7-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-3.7-flash-high`. Category: overall. Source rank: #13. Votes: 21539. Organization: google. License: Proprietary.

96.8% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,482 - 1,492

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 #7 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 98.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: creative_writing. Source rank: #7. Votes: 4776. Organization: google. License: Proprietary.

98.4% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,481 - 1,500

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 #17 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: english. Source rank: #17. Votes: 8659. Organization: google. License: Proprietary.

95.7% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,477 - 1,491

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 #13 · Source label: gemini-3.7-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-3.7-flash-high`. Category: exclude_ties. Source rank: #13. Votes: 16101. Organization: google. License: Proprietary.

96.8% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,492 - 1,505

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 #15 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: hard_prompts. Source rank: #15. Votes: 14188. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,490 - 1,502

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 #22 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,489
Percentile: 94.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: hard_prompts_english. Source rank: #22. Votes: 5704. Organization: google. License: Proprietary.

94.4% percentile inside its fair comparison set

1,489Raw benchmark valueCI 1,480 - 1,497

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 #14 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 96.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: instruction_following. Source rank: #14. Votes: 7768. Organization: google. License: Proprietary.

96.5% percentile inside its fair comparison set

1,483Raw benchmark valueCI 1,476 - 1,491

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 #14 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,493
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: longer_query. Source rank: #14. Votes: 10222. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,493Raw benchmark valueCI 1,486 - 1,500

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 #13 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,490
Percentile: 96.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: multi_turn. Source rank: #13. Votes: 3282. Organization: google. License: Proprietary.

96.8% percentile inside its fair comparison set

1,490Raw benchmark valueCI 1,479 - 1,501

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 #2 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 79.9%
Percentile: 98.5%
Last updated: stale
Eligibility: headline eligible

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

98.5% percentile inside its fair comparison set

79.9%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 #13 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 85.5%
Percentile: 81.5%
Last updated: stale
Eligibility: headline eligible

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

81.5% percentile inside its fair comparison set

85.5%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 #6 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.1%
Percentile: 92.3%
Last updated: stale
Eligibility: headline eligible

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

92.3% percentile inside its fair comparison set

78.1%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 #3 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74.6%
Percentile: 96.9%
Last updated: stale
Eligibility: headline eligible

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

96.9% percentile inside its fair comparison set

74.6%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 #2 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82.3%
Percentile: 98.5%
Last updated: stale
Eligibility: headline eligible

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

98.5% percentile inside its fair comparison set

82.3%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 #3 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 84.8%
Percentile: 96.9%
Last updated: stale
Eligibility: headline eligible

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

96.9% percentile inside its fair comparison set

84.8%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 #12 · Source label: gemini-3.7-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 #25 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 66.4%
Percentile: 63.1%
Last updated: stale
Eligibility: headline eligible

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

63.1% percentile inside its fair comparison set

66.4%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 #4 · Source label: gemini-3.7-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

Coding21 benchmarks61.4%

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 #25 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 57.2%
Percentile: 87.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

87.9% percentile inside its fair comparison set

57.2%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 #41 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,518
Percentile: 89.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: coding. Source rank: #41. Votes: 6041. Organization: google. License: Proprietary.

89.2% percentile inside its fair comparison set

1,518Raw benchmark valueCI 1,510 - 1,526

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 #24 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,498
Percentile: 93.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: coding. Source rank: #24. Votes: 6041. Organization: google. License: Proprietary.

93.8% percentile inside its fair comparison set

1,498Raw benchmark valueCI 1,490 - 1,506

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 #32 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 70.4%
Percentile: 66.7%
Last updated: recent
Eligibility: headline eligible

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

66.7% percentile inside its fair comparison set

70.4%Raw benchmark valueCI 60.9% - 79.9%

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 #26 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,592
Percentile: 80.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: overall. Source rank: #27. Votes: 9624. Organization: google. License: Proprietary.

80.3% percentile inside its fair comparison set

1,592Raw benchmark valueCI 1,584 - 1,599

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 #22 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,604
Percentile: 83.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: webdev-html. Source rank: #23. Votes: 1363. Organization: google. License: Proprietary.

83.2% percentile inside its fair comparison set

1,604Raw benchmark valueCI 1,586 - 1,622

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 #27 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,589
Percentile: 77%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: webdev-react. Source rank: #28. Votes: 6433. Organization: google. License: Proprietary.

77% percentile inside its fair comparison set

1,589Raw benchmark valueCI 1,580 - 1,598

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 #34 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 34.8%
Percentile: 51.5%
Last updated: recent
Eligibility: headline eligible

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

51.5% percentile inside its fair comparison set

34.8%Raw benchmark valueCI 26.5% - 43.1%

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 #13 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 67.8%
Percentile: 67.6%
Last updated: recent
Eligibility: headline eligible

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

67.6% percentile inside its fair comparison set

67.8%Raw benchmark valueCI 60.8% - 74.9%

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 #33 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 0%
Percentile: 51.7%
Last updated: recent
Eligibility: headline eligible

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

51.7% percentile inside its fair comparison set

0%Raw benchmark valueCI 0% - 0%

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 #14 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 77.5%
Percentile: 80.6%
Last updated: recent
Eligibility: headline eligible

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

80.6% percentile inside its fair comparison set

77.5%Raw benchmark valueCI 76.3% - 78.8%

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 #22 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 80.8%
Percentile: 74.4%
Last updated: recent
Eligibility: headline eligible

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

74.4% percentile inside its fair comparison set

80.8%Raw benchmark valueCI 77.3% - 84.3%

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 #5 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.7%
Percentile: 96.8%
Last updated: recent
Eligibility: headline eligible

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

96.8% percentile inside its fair comparison set

88.7%Raw benchmark valueCI 86.8% - 90.5%

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 #27 · Source label: Gemini 3.7 Flash (high)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Terminal-Bench
Raw value: 11.2%
Percentile: 0%
Last updated: aging
Eligibility: headline eligible

0% percentile inside its fair comparison set

11.2%Raw benchmark valueCI 8.8% - 13.7%

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 #19 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 58.3%
Percentile: 72.3%
Last updated: stale
Eligibility: headline eligible

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

72.3% percentile inside its fair comparison set

58.3%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 #29 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.9%
Percentile: 56.9%
Last updated: stale
Eligibility: headline eligible

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

56.9% percentile inside its fair comparison set

78.9%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 #24 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68.2%
Percentile: 78.5%
Last updated: stale
Eligibility: headline eligible

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

78.5% percentile inside its fair comparison set

68.2%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 #21 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 46.7%
Percentile: 72.3%
Last updated: stale
Eligibility: headline eligible

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

72.3% percentile inside its fair comparison set

46.7%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 #19 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 60%
Percentile: 80%
Last updated: stale
Eligibility: headline eligible

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

80% percentile inside its fair comparison set

60%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 #13 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 81.7%
Percentile: 83.1%
Last updated: stale
Eligibility: headline eligible

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

83.1% percentile inside its fair comparison set

81.7%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 #47 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 76.1%
Percentile: 40%
Last updated: stale
Eligibility: headline eligible

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

40% percentile inside its fair comparison set

76.1%Raw benchmark value

Reasoning / math / science18 benchmarks82.1%

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 #32 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 47.9%
Percentile: 94.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

94.1% percentile inside its fair comparison set

47.9%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 #6 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 94.5%
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `gpqa`.

99% percentile inside its fair comparison set

94.5%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 #69 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 14.3%
Percentile: 85.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

85.1% percentile inside its fair comparison set

14.3%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 #12 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 96.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: math. Source rank: #12. Votes: 1097. Organization: google. License: Proprietary.

96.9% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,485 - 1,521

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 #10 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,507
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: math. Source rank: #10. Votes: 1097. Organization: google. License: Proprietary.

97.5% percentile inside its fair comparison set

1,507Raw benchmark valueCI 1,489 - 1,525

ProofBench

VALS-AI · Reasoning / math / science · Objective

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

Rank #19 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 58%
Percentile: 57.1%
Last updated: recent
Eligibility: headline eligible

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

57.1% percentile inside its fair comparison set

58%Raw benchmark valueCI 48.3% - 67.7%

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 #5 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 93.9%
Percentile: 96.8%
Last updated: recent
Eligibility: headline eligible

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

96.8% percentile inside its fair comparison set

93.9%Raw benchmark valueCI 91% - 96.9%

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 #6 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 90.1%
Percentile: 96%
Last updated: recent
Eligibility: headline eligible

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

96% percentile inside its fair comparison set

90.1%Raw benchmark valueCI 89.5% - 90.7%

Mathematics

LB · Reasoning / math / science · Objective

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

Rank #20 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 93.5%
Percentile: 70.8%
Last updated: stale
Eligibility: headline eligible

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

70.8% percentile inside its fair comparison set

93.5%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 #25 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 87.8%
Percentile: 63.1%
Last updated: stale
Eligibility: headline eligible

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

63.1% percentile inside its fair comparison set

87.8%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 #32 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 83.1%
Last updated: stale
Eligibility: headline eligible

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

83.1% percentile inside its fair comparison set

98%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 #25 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 88%
Percentile: 64.6%
Last updated: stale
Eligibility: headline eligible

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

64.6% percentile inside its fair comparison set

88%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 #30 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 96.1%
Percentile: 66.2%
Last updated: stale
Eligibility: headline eligible

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

66.2% percentile inside its fair comparison set

96.1%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 #15 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 91.8%
Percentile: 78.5%
Last updated: stale
Eligibility: headline eligible

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

78.5% percentile inside its fair comparison set

91.8%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 #22 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 82.7%
Percentile: 72.3%
Last updated: stale
Eligibility: headline eligible

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

72.3% percentile inside its fair comparison set

82.7%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 #37 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 94.5%
Percentile: 44.6%
Last updated: stale
Eligibility: headline eligible

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

44.6% percentile inside its fair comparison set

94.5%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 #14 · Source label: gemini-3.7-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 #32 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 74%
Percentile: 58.5%
Last updated: stale
Eligibility: headline eligible

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

58.5% percentile inside its fair comparison set

74%Raw benchmark value

Professional reasoning33 benchmarks54.4%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #27 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,511
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: expert. Source rank: #28. Votes: 2521. Organization: google. License: Proprietary.

92% percentile inside its fair comparison set

1,511Raw benchmark valueCI 1,499 - 1,523

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 #22 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 94.3%
Last updated: recent
Eligibility: headline eligible

94.3% percentile inside its fair comparison set

1,483Raw benchmark valueCI 1,473 - 1,493

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 #6 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #6. Votes: 5743. Organization: google. License: Proprietary.

98.7% percentile inside its fair comparison set

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

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #24 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 93.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_legal_and_government. Source rank: #24. Votes: 1820. Organization: google. License: Proprietary.

93.4% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,477 - 1,506

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 #14 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,513
Percentile: 96.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_life_and_physical_and_social_science. Source rank: #14. Votes: 3613. Organization: google. License: Proprietary.

96.5% percentile inside its fair comparison set

1,513Raw benchmark valueCI 1,503 - 1,523

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #23 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,495
Percentile: 93.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_mathematical. Source rank: #24. Votes: 1333. Organization: google. License: Proprietary.

93.8% percentile inside its fair comparison set

1,495Raw benchmark valueCI 1,479 - 1,512

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #26 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 92.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_medicine_and_healthcare. Source rank: #26. Votes: 1517. Organization: google. License: Proprietary.

92.8% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,480 - 1,512

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 #30 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 92.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_software_and_it_services. Source rank: #30. Votes: 8363. Organization: google. License: Proprietary.

92.3% percentile inside its fair comparison set

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

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 #6 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,496
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_writing_and_literature_and_language. Source rank: #6. Votes: 5961. Organization: google. License: Proprietary.

98.7% percentile inside its fair comparison set

1,496Raw benchmark valueCI 1,487 - 1,504

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #23 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,507
Percentile: 93.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: expert. Source rank: #23. Votes: 2521. Organization: google. License: Proprietary.

93.3% percentile inside its fair comparison set

1,507Raw benchmark valueCI 1,495 - 1,519

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 #14 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,478
Percentile: 96.5%
Last updated: recent
Eligibility: headline eligible

96.5% percentile inside its fair comparison set

1,478Raw benchmark valueCI 1,469 - 1,488

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 #8 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,479
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #8. Votes: 5743. Organization: google. License: Proprietary.

98.1% percentile inside its fair comparison set

1,479Raw benchmark valueCI 1,470 - 1,487

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 #14 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_legal_and_government. Source rank: #14. Votes: 1820. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,479 - 1,508

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 #10 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,511
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_life_and_physical_and_social_science. Source rank: #10. Votes: 3613. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,511Raw benchmark valueCI 1,501 - 1,521

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #14 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_mathematical. Source rank: #14. Votes: 1333. Organization: google. License: Proprietary.

96.3% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,482 - 1,515

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 #17 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,488
Percentile: 95.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_medicine_and_healthcare. Source rank: #17. Votes: 1517. Organization: google. License: Proprietary.

95.4% percentile inside its fair comparison set

1,488Raw benchmark valueCI 1,473 - 1,504

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 #19 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 95.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_software_and_it_services. Source rank: #19. Votes: 8363. Organization: google. License: Proprietary.

95.2% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,492 - 1,506

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 #7 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 98.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: industry_writing_and_literature_and_language. Source rank: #7. Votes: 5961. Organization: google. License: Proprietary.

98.4% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,485 - 1,503

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #23 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 51
Percentile: 45%
Last updated: recent
Eligibility: headline eligible

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

45% percentile inside its fair comparison set

51Raw benchmark valueCI 49 - 53

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #35 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 34.6%
Percentile: 50%
Last updated: recent
Eligibility: headline eligible

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

50% percentile inside its fair comparison set

34.6%Raw benchmark valueCI 28.1% - 41.1%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #18 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 8.8%
Percentile: 75.4%
Last updated: recent
Eligibility: headline eligible

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

75.4% percentile inside its fair comparison set

8.8%Raw benchmark valueCI 4.5% - 13%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #5 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.3%
Percentile: 97%
Last updated: recent
Eligibility: headline eligible

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

97% percentile inside its fair comparison set

87.3%Raw benchmark valueCI 86.4% - 88.1%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #5 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 59%
Percentile: 94.2%
Last updated: recent
Eligibility: headline eligible

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

94.2% percentile inside its fair comparison set

59%Raw benchmark valueCI 58.5% - 59.6%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #9 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 53.4%
Percentile: 91.6%
Last updated: recent
Eligibility: headline eligible

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

91.6% percentile inside its fair comparison set

53.4%Raw benchmark valueCI 49.2% - 57.5%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #37 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 83.9%
Percentile: 62.5%
Last updated: recent
Eligibility: headline eligible

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

62.5% percentile inside its fair comparison set

83.9%Raw benchmark valueCI 80% - 87.9%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #23 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 49.2%
Percentile: 72.8%
Last updated: recent
Eligibility: headline eligible

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

72.8% percentile inside its fair comparison set

49.2%Raw benchmark valueCI 42.6% - 55.9%

SkillsBench

VALS-AI · Professional reasoning · Objective

Applied professional skills tasks.

Rank #3 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.9%
Percentile: 93.9%
Last updated: recent
Eligibility: headline eligible

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

93.9% percentile inside its fair comparison set

65.9%Raw benchmark valueCI 57% - 74.8%

TaxEval v2

VALS-AI · Professional reasoning · Objective

Answer quality on tax questions and responses.

Rank #31 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 74.7%
Percentile: 76.7%
Last updated: recent
Eligibility: headline eligible

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

76.7% percentile inside its fair comparison set

74.7%Raw benchmark valueCI 73.1% - 76.4%

Data analysis

LB · Professional reasoning · Objective

Structured data manipulation and table reasoning accuracy.

Rank #55 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 68%
Percentile: 16.9%
Last updated: stale
Eligibility: headline eligible

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

16.9% percentile inside its fair comparison set

68%Raw benchmark value

Overall

LB · Professional reasoning · Objective

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

Rank #16 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 78.8%
Percentile: 76.9%
Last updated: stale
Eligibility: headline eligible

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

76.9% percentile inside its fair comparison set

78.8%Raw benchmark value

Consecutive events

LB · Professional reasoning · Objective

Objective consecutive events score in LiveBench.

Rank #54 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 60.4%
Percentile: 18.5%
Last updated: stale
Eligibility: headline eligible

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

18.5% percentile inside its fair comparison set

60.4%Raw benchmark value

Table join

LB · Professional reasoning · Objective

Objective table join score in LiveBench.

Rank #53 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 45.5%
Percentile: 20%
Last updated: stale
Eligibility: headline eligible

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

20% percentile inside its fair comparison set

45.5%Raw benchmark value

Table reformat

LB · Professional reasoning · Objective

Objective table reformat score in LiveBench.

Rank #45 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: LiveBench
Raw value: 98%
Percentile: 61.5%
Last updated: stale
Eligibility: headline eligible

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

61.5% percentile inside its fair comparison set

98%Raw benchmark value

Long context1 benchmark92.5%

Long Context Reasoning

AA · Long context · Objective

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

Rank #36 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 81.7%
Percentile: 92.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

92.5% percentile inside its fair comparison set

81.7%Raw benchmark value

Vision understanding14 benchmarks95.8%

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 #10 · Source label: Gemini 3.7 Flash (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 85.5%
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `mmmuPro`.

95.7% percentile inside its fair comparison set

85.5%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 #6 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,296
Percentile: 96.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: overall. Source rank: #6. Votes: 3814. Organization: google. License: Proprietary.

96.4% percentile inside its fair comparison set

1,296Raw benchmark valueCI 1,286 - 1,306

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 #17 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,283
Percentile: 80.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: creative_writing_vision. Source rank: #17. Votes: 364. Organization: google. License: Proprietary.

80.5% percentile inside its fair comparison set

1,283Raw benchmark valueCI 1,250 - 1,316

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 #12 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,321
Percentile: 88.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: diagram. Source rank: #12. Votes: 973. Organization: google. License: Proprietary.

88.9% percentile inside its fair comparison set

1,321Raw benchmark valueCI 1,301 - 1,341

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 #12 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,283
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: english. Source rank: #12. Votes: 1317. Organization: google. License: Proprietary.

92% percentile inside its fair comparison set

1,283Raw benchmark valueCI 1,265 - 1,300

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 #17 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,320
Percentile: 83.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: homework. Source rank: #18. Votes: 442. Organization: google. License: Proprietary.

83.3% percentile inside its fair comparison set

1,320Raw benchmark valueCI 1,292 - 1,347

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 #7 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,311
Percentile: 94%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: ocr. Source rank: #7. Votes: 2612. Organization: google. License: Proprietary.

94% percentile inside its fair comparison set

1,311Raw benchmark valueCI 1,300 - 1,323

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 #7 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,315
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: overall. Source rank: #7. Votes: 3814. Organization: google. License: Proprietary.

95.7% percentile inside its fair comparison set

1,315Raw benchmark valueCI 1,305 - 1,325

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 #15 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,304
Percentile: 82.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: creative_writing_vision. Source rank: #15. Votes: 364. Organization: google. License: Proprietary.

82.9% percentile inside its fair comparison set

1,304Raw benchmark valueCI 1,272 - 1,337

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 #10 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,329
Percentile: 90.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: diagram. Source rank: #10. Votes: 973. Organization: google. License: Proprietary.

90.9% percentile inside its fair comparison set

1,329Raw benchmark valueCI 1,310 - 1,349

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 #12 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,303
Percentile: 92%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: english. Source rank: #12. Votes: 1317. Organization: google. License: Proprietary.

92% percentile inside its fair comparison set

1,303Raw benchmark valueCI 1,286 - 1,321

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 #16 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,330
Percentile: 84.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: homework. Source rank: #17. Votes: 442. Organization: google. License: Proprietary.

84.4% percentile inside its fair comparison set

1,330Raw benchmark valueCI 1,303 - 1,358

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 #8 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,325
Percentile: 93%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: ocr. Source rank: #8. Votes: 2612. Organization: google. License: Proprietary.

93% percentile inside its fair comparison set

1,325Raw benchmark valueCI 1,313 - 1,337

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 #5 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 89%
Percentile: 95.2%
Last updated: recent
Eligibility: headline eligible

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

95.2% percentile inside its fair comparison set

89%Raw benchmark valueCI 87.5% - 90.4%

Document understanding1 benchmark65.1%

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 #31 · Source label: google/gemini-3.7-flash

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 66.7%
Percentile: 65.1%
Last updated: recent
Eligibility: headline eligible

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

65.1% percentile inside its fair comparison set

66.7%Raw benchmark valueCI 64.8% - 68.5%

Multilingual20 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #8 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,546
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: chinese. Source rank: #8. Votes: 1681. Organization: google. License: Proprietary.

98% percentile inside its fair comparison set

1,546Raw benchmark valueCI 1,532 - 1,561

Text Arena · French

AR · Multilingual · Human

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

Rank #8 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,511
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: french. Source rank: #8. Votes: 614. Organization: google. License: Proprietary.

97.3% percentile inside its fair comparison set

1,511Raw benchmark valueCI 1,486 - 1,536

Text Arena · German

AR · Multilingual · Human

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

Rank #21 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,487
Percentile: 92.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: german. Source rank: #21. Votes: 313. Organization: google. License: Proprietary.

92.6% percentile inside its fair comparison set

1,487Raw benchmark valueCI 1,454 - 1,520

Text Arena · Japanese

AR · Multilingual · Human

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

Rank #5 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 98.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: japanese. Source rank: #5. Votes: 340. Organization: google. License: Proprietary.

98.4% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,471 - 1,538

Text Arena · Korean

AR · Multilingual · Human

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

Rank #7 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,480
Percentile: 97.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: korean. Source rank: #7. Votes: 404. Organization: google. License: Proprietary.

97.5% percentile inside its fair comparison set

1,480Raw benchmark valueCI 1,449 - 1,511

Text Arena · Non English

AR · Multilingual · Human

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

Rank #10 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,484
Percentile: 97.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: non_english. Source rank: #10. Votes: 12873. Organization: google. License: Proprietary.

97.6% percentile inside its fair comparison set

1,484Raw benchmark valueCI 1,478 - 1,491

Text Arena · Polish

AR · Multilingual · Human

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

Rank #4 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,506
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: polish. Source rank: #4. Votes: 318. Organization: google. License: Proprietary.

98.5% percentile inside its fair comparison set

1,506Raw benchmark valueCI 1,472 - 1,539

Text Arena · Russian

AR · Multilingual · Human

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

Rank #2 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,519
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: russian. Source rank: #2. Votes: 2610. Organization: google. License: Proprietary.

99.7% percentile inside its fair comparison set

1,519Raw benchmark valueCI 1,507 - 1,531

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #5 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,494
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: spanish. Source rank: #5. Votes: 639. Organization: google. License: Proprietary.

98.5% percentile inside its fair comparison set

1,494Raw benchmark valueCI 1,471 - 1,518

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #7 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,551
Percentile: 98.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: chinese. Source rank: #7. Votes: 1681. Organization: google. License: Proprietary.

98.3% percentile inside its fair comparison set

1,551Raw benchmark valueCI 1,536 - 1,566

Text Arena · French · No Style Control

AR · Multilingual · Human

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

Rank #8 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,504
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: french. Source rank: #8. Votes: 614. Organization: google. License: Proprietary.

97.3% percentile inside its fair comparison set

1,504Raw benchmark valueCI 1,479 - 1,529

Text Arena · German · No Style Control

AR · Multilingual · Human

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

Rank #13 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,491
Percentile: 95.6%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: german. Source rank: #13. Votes: 313. Organization: google. License: Proprietary.

95.6% percentile inside its fair comparison set

1,491Raw benchmark valueCI 1,458 - 1,524

Text Arena · Japanese · No Style Control

AR · Multilingual · Human

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

Rank #6 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 97.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: japanese. Source rank: #6. Votes: 340. Organization: google. License: Proprietary.

97.9% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,470 - 1,537

Text Arena · Korean · No Style Control

AR · Multilingual · Human

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

Rank #6 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,483
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: korean. Source rank: #6. Votes: 404. Organization: google. License: Proprietary.

98% percentile inside its fair comparison set

1,483Raw benchmark valueCI 1,452 - 1,514

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #9 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,485
Percentile: 97.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: non_english. Source rank: #9. Votes: 12873. Organization: google. License: Proprietary.

97.9% percentile inside its fair comparison set

1,485Raw benchmark valueCI 1,478 - 1,491

Text Arena · Polish · No Style Control

AR · Multilingual · Human

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

Rank #5 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,507
Percentile: 98%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: polish. Source rank: #5. Votes: 318. Organization: google. License: Proprietary.

98% percentile inside its fair comparison set

1,507Raw benchmark valueCI 1,474 - 1,540

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #3 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,516
Percentile: 99.4%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: russian. Source rank: #3. Votes: 2610. Organization: google. License: Proprietary.

99.4% percentile inside its fair comparison set

1,516Raw benchmark valueCI 1,504 - 1,528

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #8 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,499
Percentile: 97.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: spanish. Source rank: #8. Votes: 639. Organization: google. License: Proprietary.

97.3% percentile inside its fair comparison set

1,499Raw benchmark valueCI 1,475 - 1,523

Vision Arena · Chinese

AR · Multilingual · Human

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

Rank #1 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,377
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: chinese. Source rank: #1. Votes: 212. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,377Raw benchmark valueCI 1,336 - 1,418

Vision Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #2 · Source label: gemini-3.7-flash-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,402
Percentile: 99%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-3.7-flash-high`. Category: chinese. Source rank: #2. Votes: 212. Organization: google. License: Proprietary.

99% percentile inside its fair comparison set

1,402Raw benchmark valueCI 1,361 - 1,442

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

Arena

Oct 3, 2026

source →

official

Artificial Analysis

Oct 3, 2026

source →

official

LiveBench

Oct 3, 2026

source →

official

Terminal-Bench

Oct 3, 2026

source →

gemini-3.7-flash-high

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

gemini-3.7-flash-high

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks