Model profile · Google

gemini-4-argon-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: 17.1%
Verified coverage: 17.1%
Spread: 14.6%
Last verified: Oct 3, 2026

97%capability fit

textcodedocument3 aliases28 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 / text23 benchmarks97.8%

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 #8 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 53
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

98.7% percentile inside its fair comparison set

53Raw 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 #46 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 49.9%
Percentile: 90.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

90.1% percentile inside its fair comparison set

49.9%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 #4 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 84.9%
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

99.3% percentile inside its fair comparison set

84.9%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 #296 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $2 /1M input tokens
Percentile: 26.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

26.8% percentile inside its fair comparison set

$2 /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 #294 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $10 /1M output tokens
Percentile: 23.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

23.7% percentile inside its fair comparison set

$10 /1M output tokensRaw 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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,525
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: overall. Source rank: #1. Votes: 4932. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,525Raw benchmark valueCI 1,516 - 1,534

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,519
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: creative_writing. Source rank: #1. Votes: 1097. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,519Raw benchmark valueCI 1,499 - 1,538

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,533
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: english. Source rank: #1. Votes: 1928. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,533Raw benchmark valueCI 1,519 - 1,547

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,553
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: exclude_ties. Source rank: #1. Votes: 3693. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,553Raw benchmark valueCI 1,541 - 1,565

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,551
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: hard_prompts. Source rank: #1. Votes: 3166. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,551Raw benchmark valueCI 1,540 - 1,562

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,554
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: hard_prompts_english. Source rank: #1. Votes: 1245. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,554Raw benchmark valueCI 1,536 - 1,571

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,528
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: instruction_following. Source rank: #1. Votes: 1801. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,528Raw benchmark valueCI 1,514 - 1,543

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,544
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: longer_query. Source rank: #1. Votes: 2080. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,544Raw benchmark valueCI 1,531 - 1,558

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,554
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: multi_turn. Source rank: #1. Votes: 657. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,554Raw benchmark valueCI 1,531 - 1,578

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,533
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: overall. Source rank: #1. Votes: 4932. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,533Raw benchmark valueCI 1,525 - 1,542

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 #2 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,531
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: creative_writing. Source rank: #2. Votes: 1097. Organization: google. License: Proprietary.

99.7% percentile inside its fair comparison set

1,531Raw benchmark valueCI 1,511 - 1,550

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,539
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: english. Source rank: #1. Votes: 1928. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,539Raw benchmark valueCI 1,525 - 1,553

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,561
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: exclude_ties. Source rank: #1. Votes: 3693. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,561Raw benchmark valueCI 1,549 - 1,573

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,548
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: hard_prompts. Source rank: #1. Votes: 3166. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,548Raw benchmark valueCI 1,537 - 1,559

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,550
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: hard_prompts_english. Source rank: #1. Votes: 1245. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,550Raw benchmark valueCI 1,533 - 1,567

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,537
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: instruction_following. Source rank: #1. Votes: 1801. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,537Raw benchmark valueCI 1,523 - 1,551

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,548
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: longer_query. Source rank: #1. Votes: 2080. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,548Raw benchmark valueCI 1,535 - 1,562

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,558
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: multi_turn. Source rank: #1. Votes: 657. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,558Raw benchmark valueCI 1,534 - 1,582

Coding10 benchmarks96.3%

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 #4 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 61.8%
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

98.5% percentile inside its fair comparison set

61.8%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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,560
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: coding. Source rank: #1. Votes: 1230. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,560Raw benchmark valueCI 1,543 - 1,577

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,547
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: coding. Source rank: #1. Votes: 1230. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,547Raw benchmark valueCI 1,530 - 1,565

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 #2 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 91.9%
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

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

98.9% percentile inside its fair comparison set

91.9%Raw benchmark valueCI 88.2% - 95.6%

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 #9 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,680
Percentile: 93.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: overall. Source rank: #9. Votes: 2422. Organization: google. License: Proprietary.

93.7% percentile inside its fair comparison set

1,680Raw benchmark valueCI 1,666 - 1,693

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 #12 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,646
Percentile: 91.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: webdev-html. Source rank: #12. Votes: 193. Organization: google. License: Proprietary.

91.2% percentile inside its fair comparison set

1,646Raw benchmark valueCI 1,599 - 1,693

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 #9 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,693
Percentile: 92.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: webdev-react. Source rank: #9. Votes: 1736. Organization: google. License: Proprietary.

92.9% percentile inside its fair comparison set

1,693Raw benchmark valueCI 1,677 - 1,709

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 #2 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68.2%
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

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

98.5% percentile inside its fair comparison set

68.2%Raw benchmark valueCI 59.6% - 76.7%

IOI

VALS-AI · Coding · Objective

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

Rank #1 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 100%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

100%Raw benchmark valueCI 100% - 100%

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 #7 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 2.5%
Percentile: 89.7%
Last updated: recent
Eligibility: headline eligible

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

89.7% percentile inside its fair comparison set

2.5%Raw benchmark valueCI 0.3% - 4.7%

Reasoning / math / science5 benchmarks94.8%

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 #5 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 57.1%
Percentile: 99.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

99.2% percentile inside its fair comparison set

57.1%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 #28 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 27.1%
Percentile: 94.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

94.1% percentile inside its fair comparison set

27.1%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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,530
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: math. Source rank: #1. Votes: 255. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,530Raw benchmark valueCI 1,494 - 1,566

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,536
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: math. Source rank: #1. Votes: 255. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,536Raw benchmark valueCI 1,500 - 1,572

ProofBench

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-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 99%
Percentile: 92.9%
Last updated: recent
Eligibility: headline eligible

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

92.9% percentile inside its fair comparison set

99%Raw benchmark valueCI 97% - 101%

Professional reasoning27 benchmarks97.5%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #7 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,539
Percentile: 98.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: expert. Source rank: #7. Votes: 517. Organization: google. License: Proprietary.

98.2% percentile inside its fair comparison set

1,539Raw benchmark valueCI 1,513 - 1,565

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,522
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_business_and_management_and_financial_operations. Source rank: #1. Votes: 886. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,522Raw benchmark valueCI 1,502 - 1,543

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,521
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #1. Votes: 1281. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,521Raw benchmark valueCI 1,503 - 1,540

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #2 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,533
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_legal_and_government. Source rank: #2. Votes: 392. Organization: google. License: Proprietary.

99.7% percentile inside its fair comparison set

1,533Raw benchmark valueCI 1,502 - 1,564

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,542
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_life_and_physical_and_social_science. Source rank: #1. Votes: 806. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,542Raw benchmark valueCI 1,520 - 1,564

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,542
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_mathematical. Source rank: #1. Votes: 307. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,542Raw benchmark valueCI 1,509 - 1,575

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,547
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_medicine_and_healthcare. Source rank: #1. Votes: 318. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,547Raw benchmark valueCI 1,513 - 1,581

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,563
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_software_and_it_services. Source rank: #1. Votes: 1814. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,563Raw benchmark valueCI 1,549 - 1,577

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,522
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_writing_and_literature_and_language. Source rank: #1. Votes: 1408. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,522Raw benchmark valueCI 1,505 - 1,539

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #5 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,549
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: expert. Source rank: #5. Votes: 517. Organization: google. License: Proprietary.

98.8% percentile inside its fair comparison set

1,549Raw benchmark valueCI 1,523 - 1,575

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,527
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

100% percentile inside its fair comparison set

1,527Raw benchmark valueCI 1,506 - 1,547

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,530
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #1. Votes: 1281. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,530Raw benchmark valueCI 1,512 - 1,548

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,545
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_legal_and_government. Source rank: #1. Votes: 392. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,545Raw benchmark valueCI 1,515 - 1,576

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,552
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_life_and_physical_and_social_science. Source rank: #1. Votes: 806. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,552Raw benchmark valueCI 1,530 - 1,573

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,551
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_mathematical. Source rank: #1. Votes: 307. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,551Raw benchmark valueCI 1,518 - 1,583

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,551
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_medicine_and_healthcare. Source rank: #1. Votes: 318. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,551Raw benchmark valueCI 1,518 - 1,585

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,557
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_software_and_it_services. Source rank: #1. Votes: 1814. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,557Raw benchmark valueCI 1,543 - 1,571

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,532
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_writing_and_literature_and_language. Source rank: #1. Votes: 1408. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,532Raw benchmark valueCI 1,515 - 1,548

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #1 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 69
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

69Raw benchmark valueCI 67 - 71

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #4 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 54.8%
Percentile: 95.6%
Last updated: recent
Eligibility: headline eligible

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

95.6% percentile inside its fair comparison set

54.8%Raw benchmark valueCI 48% - 61.6%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #4 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 19.6%
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

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

95.7% percentile inside its fair comparison set

19.6%Raw benchmark valueCI 13.1% - 26.1%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #3 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.3%
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

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

98.5% percentile inside its fair comparison set

88.3%Raw benchmark valueCI 87.6% - 89%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #1 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.4%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

65.4%Raw benchmark valueCI 64.8% - 66%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #3 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 58.8%
Percentile: 97.9%
Last updated: recent
Eligibility: headline eligible

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

97.9% percentile inside its fair comparison set

58.8%Raw benchmark valueCI 54.7% - 62.9%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #15 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.4%
Percentile: 85.4%
Last updated: recent
Eligibility: headline eligible

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

85.4% percentile inside its fair comparison set

87.4%Raw benchmark valueCI 83.6% - 91.3%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #4 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 53.6%
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

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

96.3% percentile inside its fair comparison set

53.6%Raw benchmark valueCI 47% - 60.3%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #5 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 69.8%
Percentile: 91.1%
Last updated: recent
Eligibility: headline eligible

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

91.1% percentile inside its fair comparison set

69.8%Raw benchmark valueCI 69.8% - 69.8%

Long context1 benchmark87%

Long Context Reasoning

AA · Long context · Objective

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

Rank #65 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 79.7%
Percentile: 87%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

87% percentile inside its fair comparison set

79.7%Raw benchmark value

Multilingual8 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,587
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: chinese. Source rank: #1. Votes: 352. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,587Raw benchmark valueCI 1,555 - 1,619

Text Arena · Non English

AR · Multilingual · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: non_english. Source rank: #1. Votes: 3004. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,501 - 1,523

Text Arena · Russian

AR · Multilingual · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,533
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: russian. Source rank: #1. Votes: 687. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,533Raw benchmark valueCI 1,510 - 1,556

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #4 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: spanish. Source rank: #4. Votes: 201. Organization: google. License: Proprietary.

98.8% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,456 - 1,538

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,609
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: chinese. Source rank: #1. Votes: 352. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,609Raw benchmark valueCI 1,577 - 1,641

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,523
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: non_english. Source rank: #1. Votes: 3004. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,523Raw benchmark valueCI 1,511 - 1,534

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,541
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: russian. Source rank: #1. Votes: 687. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,541Raw benchmark valueCI 1,518 - 1,564

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #6 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: spanish. Source rank: #6. Votes: 201. Organization: google. License: Proprietary.

98.1% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,462 - 1,544

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

Artificial Analysis

Oct 3, 2026

source →

Model profile · Google

gemini-4-argon-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: 17.1%
Verified coverage: 17.1%
Spread: 14.6%
Last verified: Oct 3, 2026

97%capability fit

textcodedocument3 aliases28 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 / text23 benchmarks97.8%

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 #8 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 53
Percentile: 98.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `intelligenceIndex`.

98.7% percentile inside its fair comparison set

53Raw 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 #46 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 49.9%
Percentile: 90.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceAccuracy`.

90.1% percentile inside its fair comparison set

49.9%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 #4 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 84.9%
Percentile: 99.3%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `omniscienceNonHallucination`.

99.3% percentile inside its fair comparison set

84.9%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 #296 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $2 /1M input tokens
Percentile: 26.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mInputTokens`.

26.8% percentile inside its fair comparison set

$2 /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 #294 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: $10 /1M output tokens
Percentile: 23.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `price1mOutputTokens`.

23.7% percentile inside its fair comparison set

$10 /1M output tokensRaw 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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,525
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: overall. Source rank: #1. Votes: 4932. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,525Raw benchmark valueCI 1,516 - 1,534

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,519
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: creative_writing. Source rank: #1. Votes: 1097. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,519Raw benchmark valueCI 1,499 - 1,538

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,533
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: english. Source rank: #1. Votes: 1928. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,533Raw benchmark valueCI 1,519 - 1,547

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,553
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: exclude_ties. Source rank: #1. Votes: 3693. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,553Raw benchmark valueCI 1,541 - 1,565

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,551
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: hard_prompts. Source rank: #1. Votes: 3166. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,551Raw benchmark valueCI 1,540 - 1,562

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,554
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: hard_prompts_english. Source rank: #1. Votes: 1245. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,554Raw benchmark valueCI 1,536 - 1,571

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,528
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: instruction_following. Source rank: #1. Votes: 1801. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,528Raw benchmark valueCI 1,514 - 1,543

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,544
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: longer_query. Source rank: #1. Votes: 2080. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,544Raw benchmark valueCI 1,531 - 1,558

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,554
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: multi_turn. Source rank: #1. Votes: 657. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,554Raw benchmark valueCI 1,531 - 1,578

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,533
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: overall. Source rank: #1. Votes: 4932. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,533Raw benchmark valueCI 1,525 - 1,542

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 #2 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,531
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: creative_writing. Source rank: #2. Votes: 1097. Organization: google. License: Proprietary.

99.7% percentile inside its fair comparison set

1,531Raw benchmark valueCI 1,511 - 1,550

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,539
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: english. Source rank: #1. Votes: 1928. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,539Raw benchmark valueCI 1,525 - 1,553

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,561
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: exclude_ties. Source rank: #1. Votes: 3693. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,561Raw benchmark valueCI 1,549 - 1,573

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,548
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: hard_prompts. Source rank: #1. Votes: 3166. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,548Raw benchmark valueCI 1,537 - 1,559

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,550
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: hard_prompts_english. Source rank: #1. Votes: 1245. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,550Raw benchmark valueCI 1,533 - 1,567

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,537
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: instruction_following. Source rank: #1. Votes: 1801. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,537Raw benchmark valueCI 1,523 - 1,551

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,548
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: longer_query. Source rank: #1. Votes: 2080. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,548Raw benchmark valueCI 1,535 - 1,562

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,558
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: multi_turn. Source rank: #1. Votes: 657. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,558Raw benchmark valueCI 1,534 - 1,582

Coding10 benchmarks96.3%

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 #4 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 61.8%
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `scicode`.

98.5% percentile inside its fair comparison set

61.8%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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,560
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: coding. Source rank: #1. Votes: 1230. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,560Raw benchmark valueCI 1,543 - 1,577

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,547
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: coding. Source rank: #1. Votes: 1230. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,547Raw benchmark valueCI 1,530 - 1,565

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 #2 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 91.9%
Percentile: 98.9%
Last updated: recent
Eligibility: headline eligible

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

98.9% percentile inside its fair comparison set

91.9%Raw benchmark valueCI 88.2% - 95.6%

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 #9 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,680
Percentile: 93.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: overall. Source rank: #9. Votes: 2422. Organization: google. License: Proprietary.

93.7% percentile inside its fair comparison set

1,680Raw benchmark valueCI 1,666 - 1,693

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 #12 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,646
Percentile: 91.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: webdev-html. Source rank: #12. Votes: 193. Organization: google. License: Proprietary.

91.2% percentile inside its fair comparison set

1,646Raw benchmark valueCI 1,599 - 1,693

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 #9 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,693
Percentile: 92.9%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: webdev-react. Source rank: #9. Votes: 1736. Organization: google. License: Proprietary.

92.9% percentile inside its fair comparison set

1,693Raw benchmark valueCI 1,677 - 1,709

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 #2 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 68.2%
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

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

98.5% percentile inside its fair comparison set

68.2%Raw benchmark valueCI 59.6% - 76.7%

IOI

VALS-AI · Coding · Objective

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

Rank #1 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 100%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

100%Raw benchmark valueCI 100% - 100%

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 #7 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 2.5%
Percentile: 89.7%
Last updated: recent
Eligibility: headline eligible

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

89.7% percentile inside its fair comparison set

2.5%Raw benchmark valueCI 0.3% - 4.7%

Reasoning / math / science5 benchmarks94.8%

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 #5 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 57.1%
Percentile: 99.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `hle`.

99.2% percentile inside its fair comparison set

57.1%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 #28 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 27.1%
Percentile: 94.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `critpt`.

94.1% percentile inside its fair comparison set

27.1%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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,530
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: math. Source rank: #1. Votes: 255. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,530Raw benchmark valueCI 1,494 - 1,566

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,536
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: math. Source rank: #1. Votes: 255. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,536Raw benchmark valueCI 1,500 - 1,572

ProofBench

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-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 99%
Percentile: 92.9%
Last updated: recent
Eligibility: headline eligible

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

92.9% percentile inside its fair comparison set

99%Raw benchmark valueCI 97% - 101%

Professional reasoning27 benchmarks97.5%

Text Arena · Expert

AR · Professional reasoning · Human

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

Rank #7 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,539
Percentile: 98.2%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: expert. Source rank: #7. Votes: 517. Organization: google. License: Proprietary.

98.2% percentile inside its fair comparison set

1,539Raw benchmark valueCI 1,513 - 1,565

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,522
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

100% percentile inside its fair comparison set

1,522Raw benchmark valueCI 1,502 - 1,543

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,521
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #1. Votes: 1281. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,521Raw benchmark valueCI 1,503 - 1,540

Text Arena · Industry Legal And Government

AR · Professional reasoning · Human

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

Rank #2 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,533
Percentile: 99.7%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_legal_and_government. Source rank: #2. Votes: 392. Organization: google. License: Proprietary.

99.7% percentile inside its fair comparison set

1,533Raw benchmark valueCI 1,502 - 1,564

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,542
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_life_and_physical_and_social_science. Source rank: #1. Votes: 806. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,542Raw benchmark valueCI 1,520 - 1,564

Text Arena · Industry Mathematical

AR · Professional reasoning · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,542
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_mathematical. Source rank: #1. Votes: 307. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,542Raw benchmark valueCI 1,509 - 1,575

Text Arena · Industry Medicine And Healthcare

AR · Professional reasoning · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,547
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_medicine_and_healthcare. Source rank: #1. Votes: 318. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,547Raw benchmark valueCI 1,513 - 1,581

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,563
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_software_and_it_services. Source rank: #1. Votes: 1814. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,563Raw benchmark valueCI 1,549 - 1,577

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,522
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_writing_and_literature_and_language. Source rank: #1. Votes: 1408. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,522Raw benchmark valueCI 1,505 - 1,539

Text Arena · Expert · No Style Control

AR · Professional reasoning · Human

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

Rank #5 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,549
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: expert. Source rank: #5. Votes: 517. Organization: google. License: Proprietary.

98.8% percentile inside its fair comparison set

1,549Raw benchmark valueCI 1,523 - 1,575

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,527
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

100% percentile inside its fair comparison set

1,527Raw benchmark valueCI 1,506 - 1,547

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,530
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_entertainment_and_sports_and_media. Source rank: #1. Votes: 1281. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,530Raw benchmark valueCI 1,512 - 1,548

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,545
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_legal_and_government. Source rank: #1. Votes: 392. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,545Raw benchmark valueCI 1,515 - 1,576

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,552
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_life_and_physical_and_social_science. Source rank: #1. Votes: 806. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,552Raw benchmark valueCI 1,530 - 1,573

Text Arena · Industry Mathematical · No Style Control

AR · Professional reasoning · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,551
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_mathematical. Source rank: #1. Votes: 307. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,551Raw benchmark valueCI 1,518 - 1,583

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,551
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_medicine_and_healthcare. Source rank: #1. Votes: 318. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,551Raw benchmark valueCI 1,518 - 1,585

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,557
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_software_and_it_services. Source rank: #1. Votes: 1814. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,557Raw benchmark valueCI 1,543 - 1,571

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 #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,532
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: industry_writing_and_literature_and_language. Source rank: #1. Votes: 1408. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,532Raw benchmark valueCI 1,515 - 1,548

Vals Index

VALS-AI · Professional reasoning · Combined

Weighted model performance across economically relevant Vals tasks.

Rank #1 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 69
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

69Raw benchmark valueCI 67 - 71

Legal Research Bench

VALS-AI · Professional reasoning · Objective

Applied legal research tasks.

Rank #4 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 54.8%
Percentile: 95.6%
Last updated: recent
Eligibility: headline eligible

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

95.6% percentile inside its fair comparison set

54.8%Raw benchmark valueCI 48% - 61.6%

Harvey's Legal Agent Benchmark

VALS-AI · Professional reasoning · Objective

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

Rank #4 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 19.6%
Percentile: 95.7%
Last updated: recent
Eligibility: headline eligible

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

95.7% percentile inside its fair comparison set

19.6%Raw benchmark valueCI 13.1% - 26.1%

LegalBench

VALS-AI · Professional reasoning · Objective

Academic legal reasoning tasks.

Rank #3 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 88.3%
Percentile: 98.5%
Last updated: recent
Eligibility: headline eligible

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

98.5% percentile inside its fair comparison set

88.3%Raw benchmark valueCI 87.6% - 89%

Finance Agent v2

VALS-AI · Professional reasoning · Objective

Core financial analyst tasks for agentic models.

Rank #1 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 65.4%
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

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

100% percentile inside its fair comparison set

65.4%Raw benchmark valueCI 64.8% - 66%

MedCode

VALS-AI · Professional reasoning · Objective

Medical billing support and coding tasks.

Rank #3 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 58.8%
Percentile: 97.9%
Last updated: recent
Eligibility: headline eligible

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

97.9% percentile inside its fair comparison set

58.8%Raw benchmark valueCI 54.7% - 62.9%

MedScribe

VALS-AI · Professional reasoning · Objective

Administrative documentation support for doctors.

Rank #15 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 87.4%
Percentile: 85.4%
Last updated: recent
Eligibility: headline eligible

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

85.4% percentile inside its fair comparison set

87.4%Raw benchmark valueCI 83.6% - 91.3%

SAGE

VALS-AI · Professional reasoning · Objective

Student Assessment with Generative Evaluation.

Rank #4 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 53.6%
Percentile: 96.3%
Last updated: recent
Eligibility: headline eligible

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

96.3% percentile inside its fair comparison set

53.6%Raw benchmark valueCI 47% - 60.3%

Public Benefits Bench

VALS-AI · Professional reasoning · Objective

Answering SNAP benefits questions across the public-benefits lifecycle.

Rank #5 · Source label: google/gemini-4-argon

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Vals AI
Raw value: 69.8%
Percentile: 91.1%
Last updated: recent
Eligibility: headline eligible

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

91.1% percentile inside its fair comparison set

69.8%Raw benchmark valueCI 69.8% - 69.8%

Long context1 benchmark87%

Long Context Reasoning

AA · Long context · Objective

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

Rank #65 · Source label: Gemini 4 Argon (High)

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Artificial Analysis
Raw value: 79.7%
Percentile: 87%
Last updated: recent
Eligibility: headline eligible

Parsed from Artificial Analysis public leaderboard field `lcr`.

87% percentile inside its fair comparison set

79.7%Raw benchmark value

Multilingual8 benchmarksn/a

Text Arena · Chinese

AR · Multilingual · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,587
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: chinese. Source rank: #1. Votes: 352. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,587Raw benchmark valueCI 1,555 - 1,619

Text Arena · Non English

AR · Multilingual · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,512
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: non_english. Source rank: #1. Votes: 3004. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,512Raw benchmark valueCI 1,501 - 1,523

Text Arena · Russian

AR · Multilingual · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,533
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: russian. Source rank: #1. Votes: 687. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,533Raw benchmark valueCI 1,510 - 1,556

Text Arena · Spanish

AR · Multilingual · Human

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

Rank #4 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,497
Percentile: 98.8%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: spanish. Source rank: #4. Votes: 201. Organization: google. License: Proprietary.

98.8% percentile inside its fair comparison set

1,497Raw benchmark valueCI 1,456 - 1,538

Text Arena · Chinese · No Style Control

AR · Multilingual · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,609
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: chinese. Source rank: #1. Votes: 352. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,609Raw benchmark valueCI 1,577 - 1,641

Text Arena · Non English · No Style Control

AR · Multilingual · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,523
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: non_english. Source rank: #1. Votes: 3004. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,523Raw benchmark valueCI 1,511 - 1,534

Text Arena · Russian · No Style Control

AR · Multilingual · Human

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

Rank #1 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,541
Percentile: 100%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: russian. Source rank: #1. Votes: 687. Organization: google. License: Proprietary.

100% percentile inside its fair comparison set

1,541Raw benchmark valueCI 1,518 - 1,564

Text Arena · Spanish · No Style Control

AR · Multilingual · Human

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

Rank #6 · Source label: gemini-4-argon-high

verified runtimeexact alias

Raw row drilldownsource row, percentile, last updated, eligibility

Source: Arena
Raw value: 1,503
Percentile: 98.1%
Last updated: recent
Eligibility: headline eligible

Parsed from Arena leaderboard dataset row `gemini-4-argon-high`. Category: spanish. Source rank: #6. Votes: 201. Organization: google. License: Proprietary.

98.1% percentile inside its fair comparison set

1,503Raw benchmark valueCI 1,462 - 1,544

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

Artificial Analysis

Oct 3, 2026

source →

gemini-4-argon-high

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks

Loading model evidence.

gemini-4-argon-high

Current snapshot.

Source-linked scores by benchmark

Source links and registry checks