Gemini 3.5 Flash

Gemini / Google

35scores
31benchmarks
cost in/out

Metadata

Gemini Closed/API

Aliases: gemini-3.5-flash, google-gemini-3.5-flash, google/gemini-3.5-flash, Gemini 3.5 Flash

Benchmark Results

Benchmark Category Rank Score Sampled
ARC-AGI-1 Agentic 16 92.50 2026-05-05
ARC-AGI-1 Agentic 65 48.83 2026-05-05
ARC-AGI-2 Agentic 12 72.08 2026-05-05
ARC-AGI-2 Agentic 52 8.89 2026-05-05
AutomationBench Agentic 1 14.50 2026-05-21
AutomationBench Agentic 3 12.60 2026-05-21
AutomationBench Agentic 4 12.20 2026-05-21
ITBench-AA Agentic 4 40.3% 2026-05-28
Vending-Bench 2 Agentic 11 5396.42 2026-05-28
DeepSWE Coding 5 28.32 2026-05-26
LiveCodeBench Coding 4 87.604% 2026-05-28
SWE-bench Verified Coding 5 78.8% 2026-05-28
Terminal-Bench 2.0 Coding 5 67.416% 2026-05-28
Terminal-Bench 2.1 Coding 2 74.157% 2026-05-28
Vibe Code Bench v1.1 Coding 11 48.683% 2026-05-28
SAGE Education 10 49.885% 2026-05-28
CorpFin v2 Finance 20 64.686% 2026-05-28
Finance Agent v2 Finance 1 57.861% 2026-05-28
MortgageTax Finance 13 68.124% 2026-05-28
TaxEval v2 Finance 20 74.366% 2026-05-28
MedCode Healthcare 3 55.825% 2026-05-28
MedScribe Healthcare 34 76.574% 2026-05-28
GPQA Diamond Intelligence 3 92.676% 2026-05-28
MMLU Pro Intelligence 5 89.515% 2026-05-28
MMMU Pro Intelligence 1 88.266% 2026-05-28
Vals Index Intelligence 4 62.054% 2026-05-28
Vals Multimodal Index Intelligence 4 62.291% 2026-05-28
Harvey Legal Agent Benchmark Legal 5 0.8% 2026-05-28
LegalBench Legal 26 83.602% 2026-05-28
ProofBench Math 9 29% 2026-05-28
Blueprint-Bench 2 Multimodal 3 0.694 +/- 0.006 2026-05-28
CAIS Text Capabilities Index Reasoning 4 48.9 2026-05-27
CAIS Risk Index Safety 27 58.2 2026-05-27
CAIS Vision Capabilities Index Vision 1 65.7 2026-05-27
Roboflow Vision Evals - Visual Understanding Vision 1 83.58% 2026-05-22