Google · model
Gemini 1.5 Pro benchmark scores
As of 2026-10-07, Gemini 1.5 Pro (Google) has measured scores on 5 benchmarks and estimated scores on 58 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 58.9% | measured |
| AA-HLE | 4.6% | measured |
| AA-SciCode | 33.1% | estimated ± 3.2 pp, high confidence |
| Artificial Analysis Intelligence Index | 7.9% | measured |
| CritPt | 0.3% | estimated ± 2.3 pp, high confidence |
| GPQA Diamond | 69.2% | estimated ± 2.2 pp, medium confidence |
| HLE | 19.4% | estimated ± 9.9 pp, low confidence |
| LiveCodeBench v6 | 72.3% | estimated ± 3.1 pp, high confidence |
| AA-Omniscience Accuracy | 17.4% | estimated ± 6.9 pp, medium confidence |
| SciCode | 33.4% | estimated ± 4.7 pp, high confidence |
| AA Coding Index | 23.6% | measured |
| AA-MMMU-Pro | 55.0% | measured |
| BioMysteryBench (human-difficult) | 35.2% | estimated ± 8.1 pp, low confidence |
| SWE-bench Verified | 43.1% | estimated ± 5.5 pp, medium confidence |
| SWE-bench Pro | 30.8% | estimated ± 6.0 pp, medium confidence |
| MMLU-Pro | 74.0% | estimated ± 3.9 pp, high confidence |
| GPQA | 50.7% | estimated ± 3.2 pp, high confidence |
| ARC-AGI-1 | 0.7% | estimated ± 5.4 pp, low confidence |
| ARC-AGI-2 | 0.3% | estimated ± 14.2 pp, low confidence |
| CursorBench 3.1 | 47.9% | estimated ± 4.8 pp, low confidence |
| CursorBench 3.2 | 13.8% | estimated ± 4.4 pp, medium confidence |
| FrontierCode 1.1 Main | 7.4% | estimated ± 3.8 pp, medium confidence |
| FrontierSWE v2 | 0.0% | estimated ± 14.8 pp, low confidence |
| OfficeQA Pro | 50.3% | estimated ± 7.2 pp, low confidence |
| Vals GPQA Diamond | 45.3% | estimated ± 7.4 pp, low confidence |
| Vals MMLU-Pro | 83.1% | estimated ± 2.5 pp, medium confidence |
| Vals SWE-bench | 50.8% | estimated ± 5.4 pp, low confidence |
| CursorBench 4.0 | 5.4% | estimated ± 1.6 pp, medium confidence |
| DeepSWE | 0.2% | estimated ± 6.4 pp, low confidence |
| HLE w/o tools | 3.6% | estimated ± 5.7 pp, low confidence |
| PostTrainBench v1.1 | 8.3% | estimated ± 6.1 pp, low confidence |
| Vibe Code Bench | 6.9% | estimated ± 10.3 pp, low confidence |
| CharXiv | 70.3% | estimated ± 7.5 pp, low confidence |
| CharXiv w/o tools | 65.3% | estimated ± 2.4 pp, medium confidence |
| C-Eval | 79.8% | estimated ± 1.0 pp, low confidence |
| MathVision | 81.5% | estimated ± 4.9 pp, high confidence |
| MMLU-Redux | 72.2% | estimated ± 2.1 pp, low confidence |
| MMMU-Pro | 67.2% | estimated ± 4.4 pp, medium confidence |
| NL2Repo | 15.6% | estimated ± 5.1 pp, low confidence |
| ScreenSpot Pro | 59.3% | estimated ± 10.7 pp, low confidence |
| SuperGPQA | 37.5% | estimated ± 10.4 pp, low confidence |
| ERQA | 0.0% | estimated ± 3.9 pp, medium confidence |
| HealthBench Hard | 0.0% | estimated ± 7.7 pp, low confidence |
| MedXpertQA (MM) | 0.5% | estimated ± 6.5 pp, low confidence |
| MMLU-Pro (Arcee) | 77.7% | estimated ± 5.4 pp, low confidence |
| React Native Evals | 70.0% | estimated ± 3.5 pp, high confidence |
| SWE-Rebench | 0.0% | estimated ± 8.9 pp, low confidence |
| ARC-AGI-3 | 1.6% | estimated ± 10.7 pp, low confidence |
| BioMysteryBench (human-solvable) | 0.2% | estimated ± 1.0 pp, low confidence |
| FrontierCode 1.1 Extended | 23.5% | estimated ± 3.4 pp, low confidence |
| HealthBench (raw) | 7.2% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 57.7% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 21.4% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 39.3% | estimated ± 1.8 pp, low confidence |
| MMMU | 71.4% | estimated ± 0.9 pp, high confidence |
| LiveCodeBench | 39.1% | estimated ± 8.9 pp, low confidence |
| OpenHarmony Bench | 35.6% | estimated ± 2.8 pp, medium confidence |
| MMLU | 81.2% | estimated ± 1.9 pp, medium confidence |
| MMMU-Pro w/ Python | 64.4% | estimated ± 1.6 pp, medium confidence |
| RealWorldQA | 72.2% | estimated ± 1.2 pp, low confidence |
| OmniDocBench 1.5 | 0.0% | estimated ± 6.4 pp, low confidence |