supermarket

Vision-language

Gemini 3.7 Flash

By Google DeepMind, in the Gemini Flash family.

Released
13 Aug 2026
Status
Legacy
Context
1M
Max output
65.5K
Input per 1M tokens
$0.75
Output per 1M tokens
$3.75
Open weights
No
License
proprietary
Parameters
—
Knowledge cutoff
Mar 2026
Reasoning
Yes
Modalities
text, image, video, audio, pdf → text

Category scores

Out of 100, from independent and third-party results only, by method category-2026-09-29.1.

Category scores
CategoryScoreRankCoverage
Knowledge & reasoning51.8122 of 4
Coding & software engineering54.5Not ranked2 of 5
Vision & multimodal understanding0.0Not ranked1 of 3
Factuality & hallucination69.281 of 1
Human preference57.793 of 5

Benchmark results

Every result we hold for this model, with who ran it and where it was published.

Knowledge & reasoning

Knowledge & reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Chess PuzzlesPuzzles solved47.0%Independenthigh14 Aug 2026Epoch AI
DTBench (Decision Theory Benchmark)Accuracy (capability questions)96.8%Third partyhigh—https://conceptualreasoning.ai/dtbench via Epoch AI
DTBench (Decision Theory Benchmark)Accuracy (capability questions)94.7%Third partymedium—https://conceptualreasoning.ai/dtbench via Epoch AI
DTBench (Decision Theory Benchmark)Accuracy (capability questions)93.3%Third partylow—https://conceptualreasoning.ai/dtbench via Epoch AI
LMCA (Language Model Conceptual Argumentation)Correlation with expert ratings (Pearson r)0.5038Third partyhigh—https://conceptualreasoning.ai/lmca via Epoch AI
LMCA (Language Model Conceptual Argumentation)Correlation with expert ratings (Pearson r)0.4922Third partymedium—https://conceptualreasoning.ai/lmca via Epoch AI
LMCA (Language Model Conceptual Argumentation)Correlation with expert ratings (Pearson r)0.4709Third partylow—https://conceptualreasoning.ai/lmca via Epoch AI
Mystery Game PuzzlesPuzzles solved37.0%Independenthigh14 Aug 2026Epoch AI

Scientific reasoning

Scientific reasoning results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
GPQA DiamondAccuracy94.8%Independenthigh14 Aug 2026Epoch AI

Mathematics

Mathematics results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
FrontierMath Tier 4Accuracy36.6%Independenthigh14 Aug 2026Epoch AI
FrontierMath Tiers 1-3Accuracy71.6%Independenthigh14 Aug 2026Epoch AI
OTIS Mock AIME 2024-2025Accuracy97.2%Independenthigh14 Aug 2026Epoch AI

Coding & software engineering

Coding & software engineering results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
DeepSWEPass@165.5%Third partymedium—https://deepswe.datacurve.ai/ via Epoch AI
DeepSWEPass@165.3%Third partyhigh—https://deepswe.datacurve.ai/ via Epoch AI
DeepSWEPass@153.8%Third partylow—https://deepswe.datacurve.ai/ via Epoch AI
FrontierCodeMain score (Mean@5)43.6%Third partyunknown—https://cognition.com/frontiercode via Epoch AI

Professional knowledge work

Professional knowledge work results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
APEX-AgentsPass@1 (all rubric criteria met)67.8%Source not statedunknown—Epoch AI via Epoch AI

Vision & multimodal understanding

Vision & multimodal understanding results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Furniture AssemblyScore26.7%Independenthigh10 Sep 2026Epoch AI

Factuality & hallucination

Factuality & hallucination results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
SimpleQA VerifiedAccuracy (% correct)69.2%Independenthigh27 Aug 2026Epoch AI

Human preference

Human preference results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Code Arena: WebDev (arena.ai)Arena score (Elo scale)1593Independenthigh25 Sep 2026Arena
Code Arena: WebDev (arena.ai)Votes8086Independenthigh25 Sep 2026Arena
Text Arena (arena.ai)Arena score (Elo scale)1488Independenthigh25 Sep 2026Arena
Text Arena (arena.ai)Votes19044Independenthigh25 Sep 2026Arena
Vision Arena (arena.ai)Arena score (Elo scale)1295Independenthigh28 Sep 2026Arena
Vision Arena (arena.ai)Votes3425Independenthigh28 Sep 2026Arena

Other Gemini Flash versions

Sources