Google · model
Gemini 2.5 Pro benchmark scores
As of 2026-10-07, Gemini 2.5 Pro (Google) has measured scores on 21 benchmarks and estimated scores on 89 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 84.4% | measured |
| AA-HLE | 22.5% | measured |
| AA-SciCode | 46.3% | measured |
| AIME26 | 95.5% | estimated ± 0.6 pp, medium confidence |
| Artificial Analysis Intelligence Index | 16.1% | measured |
| CritPt | 2.6% | measured |
| GDPval-AA | 0.0% | measured |
| GPQA Diamond | 83.0% | estimated ± 0.4 pp, high confidence |
| HLE | 18.8% | measured |
| IFBench | 57.1% | estimated ± 6.9 pp, medium confidence |
| AA-LCR | 69.0% | measured |
| LiveCodeBench v6 | 78.0% | estimated ± 3.1 pp, high confidence |
| AA-Omniscience Accuracy | 39.1% | measured |
| SciCode | 46.1% | estimated ± 3.2 pp, high confidence |
| BrowseComp | 59.1% | estimated ± 5.7 pp, medium confidence |
| HLE w/ tools | 31.6% | estimated ± 6.1 pp, low confidence |
| IFEval | 91.1% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 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 ± 10.0 pp, low confidence |
| APEX-Agents-AA | 4.7% | estimated ± 9.1 pp, medium confidence |
| BioMysteryBench (human-difficult) | 40.5% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 48.1% | estimated ± 4.5 pp, medium confidence |
| SWE-bench Verified | 63.8% | measured |
| AutomationBench | 28.4% | estimated ± 9.7 pp, low confidence |
| BFCL v4 | 53.8% | estimated ± 2.6 pp, high confidence |
| CyberGym | 48.3% | estimated ± 5.3 pp, low confidence |
| JobBench | 0.0% | estimated ± 8.6 pp, low confidence |
| SWE-bench Pro | 38.0% | estimated ± 3.2 pp, high confidence |
| τ³-bench results | 69.1% | estimated ± 8.9 pp, medium confidence |
| WideResearch | 62.8% | estimated ± 5.9 pp, low confidence |
| AA Agentic Index | 3.6% | measured |
| MMLU-Pro | 84.4% | estimated ± 3.0 pp, high confidence |
| FrontierMath v2 (Tier 4) | 4.2% | measured |
| FrontierMath v2 (Tiers 1-3) | 14.1% | measured |
| GPQA | 83.0% | measured |
| AA-IFBench | 48.7% | measured |
| Gert Labs | 42.0% | measured |
| AA-AnalystAgent | 0.0% | estimated ± 12.0 pp, low confidence |
| AA EnterpriseOps-Gym | 3.6% | estimated ± 3.6 pp, low confidence |
| AA Harvey LAB | 79.4% | estimated ± 1.2 pp, low confidence |
| ApprenticeBench | 0.0% | estimated ± 3.1 pp, low confidence |
| ARC-AGI-1 | 24.1% | estimated ± 5.4 pp, low confidence |
| ARC-AGI-2 | 7.8% | estimated ± 11.6 pp, low confidence |
| CursorBench 3.1 | 34.9% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 20.7% | estimated ± 4.4 pp, medium confidence |
| FrontierCode 1.1 Main | 0.8% | estimated ± 2.7 pp, low confidence |
| FrontierSWE v2 | 3.4% | estimated ± 9.5 pp, low confidence |
| OfficeQA Pro | 50.3% | estimated ± 7.2 pp, low confidence |
| OSWorld-Verified | 55.2% | estimated ± 5.9 pp, medium confidence |
| Vals GPQA Diamond | 75.3% | estimated ± 4.8 pp, high confidence |
| Vals LiveCodeBench | 54.6% | estimated ± 9.9 pp, low confidence |
| Vals MMLU-Pro | 78.0% | estimated ± 1.2 pp, high confidence |
| Vals SWE-bench | 54.4% | measured |
| AA AutomationBench | 3.7% | estimated ± 7.0 pp, low confidence |
| GDP.pdf | 9.4% | estimated ± 5.4 pp, low confidence |
| AA ITBench | 90.7% | estimated ± 3.6 pp, low confidence |
| AA Tau3 Banking | 22.0% | estimated ± 5.8 pp, low confidence |
| CursorBench 4.0 | 8.5% | estimated ± 1.6 pp, medium confidence |
| CWE-bench v1 | 0.0% | estimated ± 6.9 pp, low confidence |
| DeepSWE | 1.4% | estimated ± 6.4 pp, low confidence |
| HLE w/o tools | 16.7% | estimated ± 4.9 pp, high confidence |
| OSWorld 2.0 | 0.0% | estimated ± 4.5 pp, low confidence |
| PostTrainBench v1.1 | 14.2% | estimated ± 3.3 pp, medium confidence |
| Toolathlon-Verified | 13.0% | estimated ± 2.3 pp, low confidence |
| Vibe Code Bench | 0.4% | measured |
| CharXiv | 81.3% | estimated ± 7.5 pp, low confidence |
| CharXiv w/o tools | 79.5% | estimated ± 2.4 pp, high confidence |
| ExploitGym | 0.0% | estimated ± 12.2 pp, low confidence |
| C-Eval | 86.4% | estimated ± 0.8 pp, low confidence |
| Claw-Eval | 56.3% | estimated ± 6.8 pp, low confidence |
| HMMT Nov 2025 | 93.3% | estimated ± 2.6 pp, medium confidence |
| MathVision | 86.0% | estimated ± 4.9 pp, high confidence |
| MCP Atlas | 64.6% | estimated ± 7.8 pp, low confidence |
| MCP-Tasks | 92.3% | estimated ± 8.2 pp, low confidence |
| MMAnswerBench | 82.9% | estimated ± 1.3 pp, medium confidence |
| MMLU-Redux | 96.6% | estimated ± 1.1 pp, medium confidence |
| MMMU-Pro | 76.9% | estimated ± 4.4 pp, medium confidence |
| NL2Repo | 37.1% | estimated ± 4.7 pp, medium confidence |
| QwenClawBench | 55.9% | estimated ± 6.0 pp, low confidence |
| ScreenSpot Pro | 73.6% | estimated ± 10.7 pp, low confidence |
| SuperGPQA | 80.7% | estimated ± 7.5 pp, medium confidence |
| Toolathlon | 26.9% | estimated ± 6.3 pp, low confidence |
| ERQA | 62.7% | estimated ± 3.9 pp, high confidence |
| HealthBench Hard | 0.0% | estimated ± 5.1 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 | 45.6% | estimated ± 2.4 pp, low confidence |
| ResearchClawBench | 6.1% | estimated ± 2.0 pp, medium confidence |
| SWE-Rebench | 57.0% | estimated ± 3.6 pp, low confidence |
| ARC-AGI-3 | 0.0% | estimated ± 2.1 pp, medium confidence |
| FrontierMath (legacy) | 15.1% | estimated ± 0.7 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| DRACO | 61.5% | estimated ± 3.0 pp, low confidence |
| FrontierCode 1.1 Extended | 3.9% | estimated ± 2.4 pp, low confidence |
| HealthBench (raw) | 30.9% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 36.8% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 42.7% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 68.8% | estimated ± 1.8 pp, low confidence |
| MMMU | 82.9% | estimated ± 0.9 pp, high confidence |
| LiveCodeBench | 58.7% | estimated ± 8.9 pp, low confidence |
| OpenHarmony Bench | 51.0% | estimated ± 2.4 pp, high confidence |
| MMLU | 93.2% | estimated ± 1.1 pp, low confidence |
| MMMU-Pro w/ Python | 78.6% | estimated ± 1.6 pp, high confidence |
| RealWorldQA | 84.9% | estimated ± 1.2 pp, medium confidence |
| OmniDocBench 1.5 | 86.7% | estimated ± 6.4 pp, low confidence |