Google · model
Gemini 2.5 Pro benchmark scores
As of 2026-11-22, Gemini 2.5 Pro (Google) has measured scores on 27 benchmarks and estimated scores on 123 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 84.4% | measured |
| AA-HLE | 22.5% | measured |
| AA-SciCode | 46.3% | measured |
| AIME26 | 95.9% | estimated ± 1.2 pp, low confidence |
| Artificial Analysis Intelligence Index | 16.1% | measured |
| CritPt | 2.6% | measured |
| GDPval-AA | 0.0% | measured |
| GPQA Diamond | 83.1% | estimated ± 1.2 pp, high confidence |
| HLE | 18.8% | measured |
| IFBench | 55.6% | estimated ± 6.6 pp, medium confidence |
| AA-LCR | 69.0% | measured |
| LiveCodeBench v6 | 79.8% | estimated ± 4.7 pp, high confidence |
| AA-Omniscience Accuracy | 39.1% | measured |
| SciCode | 46.3% | estimated ± 3.1 pp, high confidence |
| BrowseComp | 70.7% | estimated ± 8.8 pp, medium confidence |
| HLE w/ tools | 33.8% | estimated ± 5.3 pp, low confidence |
| IFEval | 90.9% | estimated ± 2.8 pp, high confidence |
| LongBench v2 | 58.0% | estimated ± 5.5 pp, medium confidence |
| τ²-bench results | 54.1% | measured |
| AA Coding Index | 33.3% | measured |
| AA-MMMU-Pro | 74.9% | measured |
| APEX-Agents | 0.0% | estimated ± 9.4 pp, low confidence |
| APEX-Agents-AA | 16.3% | estimated ± 9.3 pp, medium confidence |
| BioMysteryBench (human-difficult) | 29.1% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 48.1% | estimated ± 4.5 pp, medium confidence |
| SWE-bench Verified | 63.8% | measured |
| BFCL v4 | 53.9% | estimated ± 2.7 pp, high confidence |
| CyberGym | 48.3% | estimated ± 5.3 pp, low confidence |
| JobBench | 0.0% | estimated ± 8.7 pp, low confidence |
| SWE-bench Pro | 53.0% | estimated ± 2.9 pp, low confidence |
| WideResearch | 72.7% | estimated ± 3.3 pp, high confidence |
| AA Agentic Index | 3.6% | measured |
| MMLU-Pro | 83.9% | estimated ± 4.4 pp, high confidence |
| AA-IFBench | 48.7% | measured |
| AIME 2024 | 92.0% | measured |
| FailureSensorIQ | 67.0% | measured |
| GPQA | 83.0% | measured |
| MMLU | 90.5% | estimated ± 0.9 pp, medium confidence |
| Vals GPQA Diamond | 85.1% | estimated ± 3.1 pp, medium confidence |
| Vals LiveCodeBench | 81.1% | estimated ± 5.7 pp, low confidence |
| Vals MMLU-Pro | 84.2% | estimated ± 1.8 pp, high confidence |
| MATH-500 | 97.7% | estimated ± 1.3 pp, medium confidence |
| MMMLU | 87.5% | estimated ± 0.7 pp, medium confidence |
| MMMU | 83.3% | estimated ± 2.7 pp, high confidence |
| AIME 2025 | 89.4% | estimated ± 3.5 pp, high confidence |
| AA MMLU-Pro | 86.2% | measured |
| Gert Labs | 32.6% | measured |
| AA Harvey LAB v1.0 | 79.4% | estimated ± 1.2 pp, low confidence |
| AA Tau3 Banking | 18.1% | estimated ± 3.7 pp, medium confidence |
| ApprenticeBench | 3.4% | estimated ± 10.4 pp, low confidence |
| ARC-AGI-1 | 60.7% | estimated ± 6.7 pp, medium confidence |
| ARC-AGI-2 | 8.6% | estimated ± 10.9 pp, low confidence |
| CursorBench 3.1 | 34.9% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 47.8% | estimated ± 5.3 pp, low confidence |
| FrontierCode 1.1 Main | 0.0% | estimated ± 4.2 pp, low confidence |
| FrontierMath v2 (Tier 4) | 0.0% | measured |
| FrontierMath v2 (Tiers 1-3) | 24.6% | measured |
| FrontierSWE v2 | 12.3% | estimated ± 14.2 pp, low confidence |
| MazeBench | 0.1% | estimated ± 2.7 pp, high confidence |
| Mystery Game Puzzles | 6.4% | estimated ± 4.7 pp, medium confidence |
| OfficeQA Pro | 50.3% | estimated ± 6.8 pp, low confidence |
| OSWorld-Verified | 55.4% | estimated ± 8.4 pp, low confidence |
| ParseBench-1 | 59.0% | estimated ± 6.2 pp, medium confidence |
| Vals SWE-bench | 54.4% | measured |
| CWE-Bench-AA | 42.0% | estimated ± 8.1 pp, medium confidence |
| AA Cyber Index | 2.6% | estimated ± 9.2 pp, low confidence |
| DeepsecBench-AA | 10.1% | estimated ± 8.2 pp, low confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 50.7% | estimated ± 4.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 29.0% | estimated ± 0.8 pp, low confidence |
| AA ITBench | 34.0% | estimated ± 4.0 pp, medium confidence |
| Bug Hunt Bench | 19.1% | estimated ± 10.5 pp, low confidence |
| Chartography (tools) | 80.2% | estimated ± 4.1 pp, low confidence |
| CursorBench 4.0 | 32.6% | estimated ± 4.9 pp, medium confidence |
| CWE-bench v1 | 40.9% | estimated ± 5.7 pp, medium confidence |
| DeepSWE | 49.3% | estimated ± 7.5 pp, low confidence |
| DRACO | 0.0% | estimated ± 2.0 pp, low confidence |
| FrontierCode 2.0 | 26.1% | estimated ± 9.3 pp, low confidence |
| HLE w/o tools | 28.7% | estimated ± 4.9 pp, high confidence |
| OSWorld 2.1 | 17.5% | estimated ± 3.6 pp, medium confidence |
| OSWorld 2.1 Offline | 42.7% | estimated ± 10.1 pp, low confidence |
| PostTrainBench v1.1 | 27.3% | estimated ± 7.4 pp, low confidence |
| Toolathlon-Verified | 13.0% | estimated ± 2.3 pp, low confidence |
| VulcanBench Frontier v4 | 76.5% | estimated ± 6.8 pp, low confidence |
| AA AutomationBench | 44.7% | estimated ± 9.9 pp, low confidence |
| GDP.pdf | 14.4% | estimated ± 4.2 pp, medium confidence |
| ARC-AGI-3 | 1.3% | estimated ± 9.8 pp, medium confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| cursorBench41 | 44.8% | estimated ± 3.7 pp, medium confidence |
| CWE-bench | 35.2% | estimated ± 6.2 pp, low confidence |
| MKA | 33.0% | estimated ± 4.6 pp, medium confidence |
| SkillsBench official leaderboard (BenchFlow) | 44.1% | estimated ± 9.5 pp, low confidence |
| BinaryAudit | 21.1% | measured |
| CompileBench | 53.3% | measured |
| OTelBench | 19.6% | estimated ± 5.6 pp, medium confidence |
| Vibe Code Bench | 0.4% | measured |
| Hermes Bench | 0.0% | estimated ± 2.9 pp, medium confidence |
| Hermes Index | 22.0% | estimated ± 5.7 pp, low confidence |
| ParseBench-2 | 64.4% | estimated ± 6.2 pp, medium confidence |
| CharXiv | 80.8% | estimated ± 6.3 pp, low confidence |
| CharXiv w/o tools | 80.1% | estimated ± 2.5 pp, high confidence |
| ExploitGym | 0.0% | estimated ± 8.3 pp, low confidence |
| AI2D_TEST | 91.4% | estimated ± 2.0 pp, medium confidence |
| C-Eval | 88.8% | estimated ± 0.9 pp, low confidence |
| CountBench | 94.9% | estimated ± 2.9 pp, medium confidence |
| DynaMath | 85.2% | estimated ± 3.0 pp, medium confidence |
| ERQA | 62.9% | estimated ± 3.1 pp, high confidence |
| HMMT Feb 2026 | 83.5% | estimated ± 1.5 pp, low confidence |
| HMMT Nov 2025 | 90.7% | estimated ± 1.5 pp, medium confidence |
| MathVision | 85.1% | estimated ± 3.1 pp, high confidence |
| MCP Atlas | 64.6% | estimated ± 7.8 pp, low confidence |
| MMAnswerBench | 80.1% | estimated ± 2.4 pp, medium confidence |
| MMLU-Redux | 95.9% | estimated ± 0.8 pp, medium confidence |
| MMMU-Pro | 76.1% | estimated ± 1.5 pp, high confidence |
| NL2Repo | 36.3% | estimated ± 4.7 pp, medium confidence |
| PostTrainBench v1 | 19.0% | estimated ± 3.1 pp, low confidence |
| QwenClawBench | 55.9% | estimated ± 6.0 pp, low confidence |
| RealWorldQA | 82.9% | estimated ± 2.9 pp, medium confidence |
| ScreenSpot Pro | 74.4% | estimated ± 10.8 pp, low confidence |
| SuperGPQA | 59.9% | estimated ± 7.2 pp, medium confidence |
| Toolathlon | 27.0% | estimated ± 6.3 pp, low confidence |
| V* | 100.0% | estimated ± 7.5 pp, medium confidence |
| Video-MME (w/o subtitle) | 83.0% | estimated ± 1.7 pp, medium confidence |
| Video-MME (with subtitle) | 85.0% | estimated ± 3.7 pp, medium confidence |
| AA LiveCodeBench | 80.1% | measured |
| HealthBench Hard | 17.7% | estimated ± 8.6 pp, low confidence |
| MedXpertQA (MM) | 71.9% | estimated ± 6.5 pp, low confidence |
| MMLU-Pro (Arcee) | 86.9% | estimated ± 4.0 pp, medium confidence |
| React Native Evals | 72.4% | estimated ± 2.7 pp, medium confidence |
| ResearchClawBench | 6.0% | estimated ± 1.9 pp, medium confidence |
| SWE-Rebench | 57.0% | estimated ± 3.6 pp, low confidence |
| PostTrainBench | 17.0% | estimated ± 8.3 pp, low confidence |
| Finance Agent v2 | 55.1% | estimated ± 2.4 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (raw) | 30.7% | estimated ± 6.0 pp, low confidence |
| HealthBench (length-adjusted) | 46.9% | estimated ± 3.4 pp, low confidence |
| HealthBench Professional | 56.7% | estimated ± 4.2 pp, low confidence |
| HealthBench Professional (raw) | 42.5% | estimated ± 4.5 pp, medium confidence |
| HLE-Verified | 33.8% | estimated ± 7.1 pp, low confidence |
| ScarfBench | 24.4% | estimated ± 9.1 pp, low confidence |
| STEMBench | 2.5% | estimated ± 0.2 pp, medium confidence |
| SimpleQA | 44.3% | estimated ± 4.3 pp, low confidence |
| LiveCodeBench | 68.7% | estimated ± 14.6 pp, low confidence |
| Agents' Last Exam | 29.7% | estimated ± 9.7 pp, low confidence |
| BabyVision w/ Python | 87.6% | estimated ± 4.0 pp, low confidence |
| OpenHarmony Bench v1.0 | 51.0% | estimated ± 2.4 pp, high confidence |
| MRCRv2 | 69.6% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 60.9% | estimated ± 2.6 pp, low confidence |
| BioBasicsBench | 33.9% | estimated ± 2.8 pp, low confidence |
| LifeVal | 10.9% | estimated ± 5.0 pp, low confidence |
| MMMU-Pro w/ Python | 78.1% | estimated ± 2.0 pp, high confidence |