Google · model
Gemini 3.6 Flash benchmark scores
As of 2026-11-22, Gemini 3.6 Flash (Google) has measured scores on 34 benchmarks and estimated scores on 141 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 92.8% | measured |
| AA-HLE | 40.8% | measured |
| AA-SciCode | 53.4% | measured |
| AIME26 | 95.9% | estimated ± 1.2 pp, medium confidence |
| Artificial Analysis Intelligence Index | 34.0% | measured |
| CritPt | 10.6% | measured |
| GDPval-AA | 39.2% | measured |
| GPQA Diamond | 91.4% | estimated ± 1.4 pp, high confidence |
| HLE | 46.0% | estimated ± 6.1 pp, medium confidence |
| AA-LCR | 80.0% | measured |
| LiveCodeBench v6 | 90.1% | estimated ± 2.2 pp, low confidence |
| AA-Omniscience Accuracy | 50.0% | measured |
| SciCode | 52.9% | estimated ± 2.9 pp, low confidence |
| Terminal-Bench 2.1 | 85.5% | estimated ± 6.7 pp, medium confidence |
| BrowseComp | 83.8% | estimated ± 4.7 pp, high confidence |
| HLE w/ tools | 52.7% | estimated ± 5.3 pp, medium confidence |
| LongBench v2 | 65.7% | estimated ± 5.5 pp, medium confidence |
| AA Coding Index | 69.2% | measured |
| AA-MMMU-Pro | 83.2% | measured |
| APEX-Agents | 31.1% | estimated ± 9.4 pp, low confidence |
| APEX-Agents-AA | 45.7% | estimated ± 7.8 pp, low confidence |
| BioMysteryBench (human-difficult) | 44.3% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 89.2% | estimated ± 4.5 pp, high confidence |
| SWE-bench Verified | 81.7% | estimated ± 4.4 pp, high confidence |
| BFCL v4 | 75.7% | estimated ± 2.7 pp, medium confidence |
| CyberGym | 68.7% | estimated ± 5.3 pp, medium confidence |
| JobBench | 39.9% | estimated ± 8.7 pp, medium confidence |
| SWE-bench Pro | 57.0% | estimated ± 4.5 pp, high confidence |
| WideResearch | 81.4% | estimated ± 2.1 pp, medium confidence |
| AA Agentic Index | 30.2% | measured |
| MMLU-Pro | 87.3% | estimated ± 4.8 pp, high confidence |
| FailureSensorIQ | 68.0% | estimated ± 1.7 pp, high confidence |
| GPQA | 91.2% | estimated ± 1.6 pp, high confidence |
| MMLU | 90.5% | estimated ± 0.9 pp, medium confidence |
| Vals GPQA Diamond | 93.4% | measured |
| Vals LiveCodeBench | 88.1% | measured |
| Vals MMLU-Pro | 89.3% | measured |
| MMMLU | 89.6% | estimated ± 0.7 pp, medium confidence |
| MMMU | 88.3% | estimated ± 2.7 pp, medium confidence |
| Chess Puzzles | 40.0% | measured |
| AA MMLU-Pro | 88.8% | estimated ± 0.7 pp, medium confidence |
| Gert Labs | 59.5% | measured |
| AA-AnalystAgent | 44.8% | estimated ± 5.9 pp, low confidence |
| AA Harvey LAB v1.0 | 87.7% | estimated ± 1.2 pp, medium confidence |
| AA Tau3 Banking | 33.3% | estimated ± 3.7 pp, high confidence |
| AA Terminal-Bench 2.1 | 83.9% | estimated ± 2.5 pp, high confidence |
| ApprenticeBench | 25.2% | estimated ± 6.3 pp, low confidence |
| ARC-AGI-1 | 91.2% | measured |
| ARC-AGI-2 | 60.4% | measured |
| BabaIsBench | 88.0% | measured |
| CursorBench 3.1 | 52.4% | estimated ± 3.4 pp, medium confidence |
| CursorBench 3.2 | 53.5% | measured |
| EBR-bench | 9.1% | estimated ± 9.3 pp, medium confidence |
| Terminal-Bench 3.0 | 17.7% | estimated ± 6.9 pp, medium confidence |
| FrontierCode 1.1 Main | 36.5% | estimated ± 1.6 pp, low confidence |
| FrontierMath v2 (Tier 4) | 22.0% | measured |
| FrontierMath v2 (Tiers 1-3) | 58.9% | measured |
| FrontierSWE v2 | 10.1% | estimated ± 9.5 pp, medium confidence |
| Furniture Assembly | 23.3% | measured |
| MaxxBench | 49.4% | estimated ± 6.6 pp, low confidence |
| MazeBench | 0.0% | measured |
| MirrorCode | 23.3% | measured |
| Mystery Game Puzzles | 30.0% | measured |
| NYT Connections | 89.0% | measured |
| OfficeQA Pro | 67.6% | estimated ± 6.8 pp, medium confidence |
| OSWorld-Verified | 83.0% | measured |
| ParseBench-1 | 69.1% | measured |
| Terminal-Bench 4.1 | 22.8% | estimated ± 14.9 pp, low confidence |
| Terminal-Bench Hard | 56.4% | estimated ± 3.9 pp, high confidence |
| Vals SWE-bench | 79.6% | measured |
| Terminal-Bench 2.1 (Vals AI) | 73.8% | measured |
| VulcanBench v3 | 75.4% | estimated ± 5.1 pp, low confidence |
| CWE-Bench-AA | 56.0% | estimated ± 8.1 pp, medium confidence |
| AA Cyber Index | 19.3% | estimated ± 9.2 pp, low confidence |
| DeepsecBench-AA | 22.0% | estimated ± 8.2 pp, medium confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 56.2% | estimated ± 4.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 56.1% | estimated ± 0.8 pp, low confidence |
| AA ITBench | 41.0% | estimated ± 3.2 pp, high confidence |
| Bug Hunt Bench | 18.2% | estimated ± 9.0 pp, low confidence |
| Chartography (tools) | 85.3% | estimated ± 4.1 pp, low confidence |
| CursorBench 4.0 | 31.9% | estimated ± 2.0 pp, medium confidence |
| CWE-bench v1 | 57.4% | estimated ± 5.1 pp, medium confidence |
| DeepSWE | 49.0% | measured |
| DRACO | 86.9% | estimated ± 0.7 pp, low confidence |
| FrontierCode 2.0 | 16.2% | estimated ± 5.4 pp, low confidence |
| FrontierPhysics | 0.0% | estimated ± 4.4 pp, high confidence |
| HLE w/o tools | 48.2% | estimated ± 4.9 pp, high confidence |
| OSWorld 2.0 | 17.8% | estimated ± 3.6 pp, high confidence |
| OSWorld 2.1 | 72.9% | estimated ± 3.6 pp, high confidence |
| OSWorld 2.1 Offline | 26.6% | estimated ± 1.9 pp, low confidence |
| PostTrainBench v1.1 | 23.8% | estimated ± 3.7 pp, high confidence |
| ProgramBench | 62.2% | estimated ± 6.0 pp, low confidence |
| SpireClimb | 5.8% | estimated ± 7.2 pp, medium confidence |
| StealthMark | 45.2% | estimated ± 6.5 pp, medium confidence |
| SWE-bench Multimodal | 56.6% | estimated ± 5.6 pp, low confidence |
| Toolathlon-Verified | 60.0% | estimated ± 2.3 pp, medium confidence |
| VulcanBench Frontier v4 | 70.7% | estimated ± 2.3 pp, low confidence |
| AA AutomationBench | 59.4% | estimated ± 9.9 pp, low confidence |
| GDP.pdf | 22.4% | estimated ± 4.2 pp, high confidence |
| AA Terminal-Bench 4.0 | 35.3% | estimated ± 13.7 pp, low confidence |
| ARC-AGI-3 | 5.5% | estimated ± 8.6 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, medium confidence |
| cursorBench41 | 44.8% | estimated ± 3.7 pp, medium confidence |
| CWE-bench | 52.7% | estimated ± 6.2 pp, medium confidence |
| MKA | 39.7% | estimated ± 4.6 pp, high confidence |
| SkillsBench official leaderboard (BenchFlow) | 55.9% | estimated ± 6.1 pp, medium confidence |
| BinaryAudit | 35.8% | estimated ± 12.1 pp, low confidence |
| CompileBench | 100.0% | estimated ± 10.0 pp, low confidence |
| OTelBench | 32.1% | estimated ± 4.1 pp, low confidence |
| Vibe Code Bench | 51.8% | estimated ± 10.0 pp, low confidence |
| FACTS Multimodal | 53.7% | measured |
| Hermes Bench | 65.5% | estimated ± 2.9 pp, high confidence |
| Hermes Index | 37.2% | estimated ± 3.1 pp, high confidence |
| ParseBench-2 | 75.8% | measured |
| CharXiv | 87.1% | estimated ± 5.6 pp, low confidence |
| CharXiv w/o tools | 84.3% | estimated ± 1.8 pp, medium confidence |
| ExploitBench | 32.4% | estimated ± 6.5 pp, low confidence |
| ExploitGym | 10.2% | estimated ± 2.7 pp, high confidence |
| AI2D_TEST | 94.2% | estimated ± 2.0 pp, low confidence |
| C-Eval | 95.7% | estimated ± 1.0 pp, low confidence |
| Claw-Eval | 70.8% | estimated ± 6.2 pp, low confidence |
| CountBench | 100.0% | estimated ± 2.9 pp, low confidence |
| DynaMath | 85.5% | estimated ± 3.0 pp, low confidence |
| ERQA | 68.8% | estimated ± 3.1 pp, medium confidence |
| HMMT Feb 2026 | 91.8% | estimated ± 1.5 pp, medium confidence |
| HMMT Nov 2025 | 95.0% | estimated ± 1.5 pp, medium confidence |
| MathVision | 93.2% | estimated ± 3.1 pp, medium confidence |
| MCP Atlas | 78.7% | estimated ± 7.8 pp, low confidence |
| MMAnswerBench | 88.8% | estimated ± 2.4 pp, medium confidence |
| MMLU-Redux | 97.2% | estimated ± 0.8 pp, low confidence |
| MMMU-Pro | 83.2% | estimated ± 1.5 pp, high confidence |
| NL2Repo | 45.2% | estimated ± 4.7 pp, high confidence |
| PostTrainBench v1 | 23.9% | estimated ± 3.6 pp, high confidence |
| QwenClawBench | 93.2% | estimated ± 6.0 pp, low confidence |
| RealWorldQA | 88.1% | estimated ± 2.9 pp, low confidence |
| ScreenSpot Pro | 88.7% | estimated ± 10.1 pp, low confidence |
| SuperGPQA | 99.1% | estimated ± 9.3 pp, low confidence |
| Terminal-Bench 2.0 | 75.4% | estimated ± 5.8 pp, medium confidence |
| Toolathlon | 55.8% | estimated ± 6.3 pp, medium confidence |
| V* | 100.0% | estimated ± 7.5 pp, low confidence |
| Video-MME (w/o subtitle) | 89.1% | estimated ± 1.7 pp, low confidence |
| Video-MME (with subtitle) | 90.2% | estimated ± 3.7 pp, low confidence |
| AA LiveCodeBench | 91.4% | estimated ± 2.6 pp, medium confidence |
| HealthBench Hard | 29.3% | estimated ± 8.6 pp, low confidence |
| MedXpertQA (MM) | 77.6% | estimated ± 6.5 pp, low confidence |
| React Native Evals | 81.5% | estimated ± 3.2 pp, high confidence |
| ResearchClawBench | 18.8% | estimated ± 1.9 pp, high confidence |
| PostTrainBench | 21.4% | estimated ± 3.7 pp, high confidence |
| DAYJOB | 1.4% | estimated ± 2.7 pp, medium confidence |
| DAYJOB Healthcare | 0.0% | estimated ± 4.0 pp, medium confidence |
| Finance Agent v2 | 57.1% | estimated ± 2.4 pp, medium confidence |
| BioMysteryBench (human-solvable) | 83.8% | estimated ± 0.6 pp, low confidence |
| FrontierCode 1.1 Extended | 55.1% | estimated ± 1.6 pp, low confidence |
| HealthBench (raw) | 49.4% | estimated ± 6.0 pp, medium confidence |
| HealthBench (length-adjusted) | 55.6% | estimated ± 2.5 pp, low confidence |
| HealthBench Professional | 57.2% | estimated ± 4.2 pp, medium confidence |
| HealthBench Professional (raw) | 60.0% | estimated ± 4.5 pp, high confidence |
| HLE-Verified | 52.7% | estimated ± 2.0 pp, medium confidence |
| LABBench2 | 82.7% | estimated ± 1.8 pp, low confidence |
| ScarfBench | 61.3% | estimated ± 3.8 pp, low confidence |
| BlenderWorld (text-only) | 70.9% | estimated ± 2.8 pp, medium confidence |
| Cookie-Bench | 79.2% | estimated ± 1.3 pp, medium confidence |
| STEMBench | 2.6% | estimated ± 0.2 pp, medium confidence |
| SimpleQA | 35.0% | estimated ± 7.8 pp, low confidence |
| Agents' Last Exam | 34.6% | estimated ± 9.7 pp, medium confidence |
| BabyVision w/ Python | 92.8% | estimated ± 4.0 pp, low confidence |
| OpenHarmony Bench v1.0 | 58.9% | estimated ± 2.4 pp, high confidence |
| SEC-Bench Pro | 84.1% | estimated ± 5.6 pp, medium confidence |
| MRCRv2 | 85.8% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 61.4% | estimated ± 2.6 pp, low confidence |
| BioBasicsBench | 34.0% | estimated ± 2.8 pp, medium confidence |
| LifeVal | 75.2% | estimated ± 3.8 pp, medium confidence |
| MMMU-Pro w/ Python | 85.6% | estimated ± 2.0 pp, high confidence |
| ExploitBench Internal Port | 0.4% | estimated ± 1.4 pp, medium confidence |
| SWE-Atlas Codebase QnA | 44.1% | estimated ± 4.8 pp, high confidence |