Google · model
Gemini 1.5 Flash benchmark scores
As of 2026-10-29, Gemini 1.5 Flash (Google) has measured scores on 9 benchmarks and estimated scores on 45 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 46.3% | measured |
| AA-HLE | 3.2% | measured |
| AA-SciCode | 7.4% | estimated ± 3.9 pp, medium confidence |
| AIME26 | 20.5% | estimated ± 4.6 pp, low confidence |
| CritPt | 0.2% | estimated ± 2.4 pp, high confidence |
| GPQA Diamond | 50.4% | estimated ± 1.2 pp, high confidence |
| HLE | 2.1% | estimated ± 6.9 pp, low confidence |
| SciCode | 7.3% | estimated ± 3.3 pp, medium confidence |
| AA Coding Index | 23.4% | estimated ± 5.3 pp, low confidence |
| AA-MMMU-Pro | 48.4% | measured |
| SWE-bench Verified | 9.6% | measured |
| SWE-bench Pro | 0.0% | estimated ± 4.6 pp, medium confidence |
| MMLU-Pro | 66.2% | estimated ± 4.1 pp, medium confidence |
| AIME 2024 | 25.1% | estimated ± 2.6 pp, medium confidence |
| Artificial Analysis Intelligence Index | 7.1% | measured |
| BBH | 82.7% | estimated ± 4.5 pp, low confidence |
| GPQA | 50.0% | measured |
| MMLU | 81.0% | estimated ± 2.7 pp, high confidence |
| AA-Omniscience Accuracy | 13.7% | estimated ± 2.7 pp, low confidence |
| MATH-500 | 89.1% | estimated ± 2.1 pp, medium confidence |
| MMMLU | 72.5% | estimated ± 1.7 pp, high confidence |
| MMMU | 58.3% | measured |
| AA MMLU-Pro | 83.3% | estimated ± 1.1 pp, medium confidence |
| AIME 2025 | 14.7% | measured |
| ARC-AGI-1 | 59.7% | estimated ± 8.1 pp, low confidence |
| ARC-AGI-2 | 30.7% | estimated ± 14.6 pp, low confidence |
| ParseBench | 41.8% | estimated ± 5.5 pp, low confidence |
| Vals GPQA Diamond | 81.3% | estimated ± 5.3 pp, low confidence |
| Vals MMLU-Pro | 83.9% | estimated ± 2.1 pp, medium confidence |
| HLE w/o tools | 28.6% | estimated ± 4.6 pp, medium confidence |
| ARC-AGI-3 | 1.4% | estimated ± 7.7 pp, low confidence |
| CharXiv | 60.8% | estimated ± 6.2 pp, low confidence |
| AI2D_TEST | 87.3% | estimated ± 2.0 pp, high confidence |
| C-Eval | 87.7% | estimated ± 1.0 pp, low confidence |
| CountBench | 92.6% | estimated ± 3.2 pp, high confidence |
| DynaMath | 79.2% | estimated ± 5.8 pp, low confidence |
| ERQA | 47.1% | estimated ± 5.2 pp, low confidence |
| MathVision | 54.7% | estimated ± 3.6 pp, high confidence |
| MLVU (M-Avg) | 74.1% | estimated ± 2.4 pp, high confidence |
| MMLU-Redux | 87.6% | estimated ± 1.2 pp, low confidence |
| MMMU-Pro | 48.5% | estimated ± 1.6 pp, high confidence |
| RealWorldQA | 74.9% | estimated ± 3.6 pp, high confidence |
| ScreenSpot Pro | 53.0% | estimated ± 7.3 pp, low confidence |
| SimpleVQA | 42.5% | estimated ± 7.1 pp, medium confidence |
| SuperGPQA | 61.7% | estimated ± 10.1 pp, low confidence |
| Video-MME (w/o subtitle) | 64.0% | estimated ± 1.3 pp, high confidence |
| Video-MME (with subtitle) | 70.3% | estimated ± 3.2 pp, high confidence |
| VideoMMMU | 48.1% | estimated ± 3.8 pp, high confidence |
| We-Math | 68.8% | estimated ± 7.2 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.3 pp, medium confidence |
| HealthBench Professional (raw) | 49.2% | estimated ± 8.6 pp, low confidence |
| SimpleQA | 8.6% | measured |
| MMVU | 58.7% | estimated ± 3.8 pp, medium confidence |
| MMMU-Pro w/ Python | 54.3% | estimated ± 2.0 pp, medium confidence |