Google · model
Gemini 2.5 Flash-Lite benchmark scores
As of 2026-10-29, Gemini 2.5 Flash-Lite (Google) has measured scores on 14 benchmarks and estimated scores on 55 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 47.4% | measured |
| AA-HLE | 3.7% | measured |
| AA-SciCode | 22.4% | estimated ± 3.9 pp, medium confidence |
| AIME26 | 52.8% | estimated ± 4.6 pp, medium confidence |
| CritPt | 0.0% | measured |
| GDPval-AA | 0.0% | estimated ± 10.9 pp, low confidence |
| GPQA Diamond | 64.9% | estimated ± 1.2 pp, high confidence |
| HLE | 6.4% | estimated ± 6.9 pp, medium confidence |
| IFBench | 53.7% | estimated ± 6.6 pp, low confidence |
| AA-LCR | 32.0% | measured |
| SciCode | 22.2% | estimated ± 3.3 pp, medium confidence |
| IFEval | 84.8% | estimated ± 2.8 pp, high confidence |
| LongBench v2 | 53.1% | estimated ± 5.8 pp, low confidence |
| τ²-bench results | 19.0% | measured |
| AA Coding Index | 23.4% | estimated ± 5.3 pp, medium confidence |
| AA-MMMU-Pro | 54.0% | measured |
| BioMysteryBench (human-difficult) | 0.0% | estimated ± 6.8 pp, low confidence |
| SWE-bench Verified | 31.6% | measured |
| SWE-bench Pro | 4.8% | estimated ± 4.6 pp, medium confidence |
| AA Agentic Index | 0.0% | estimated ± 12.3 pp, low confidence |
| MMLU-Pro | 65.2% | estimated ± 4.1 pp, medium confidence |
| AA-IFBench | 31.5% | measured |
| AIME 2024 | 64.7% | estimated ± 2.6 pp, high confidence |
| Artificial Analysis Intelligence Index | 6.7% | measured |
| GPQA | 64.6% | measured |
| MMLU | 81.0% | estimated ± 0.7 pp, medium confidence |
| AA-Omniscience Accuracy | 15.4% | measured |
| MATH-500 | 93.4% | estimated ± 2.1 pp, high confidence |
| MMMLU | 83.3% | estimated ± 0.7 pp, medium confidence |
| MMMU | 72.9% | measured |
| AA MMLU-Pro | 82.7% | estimated ± 0.6 pp, medium confidence |
| AIME 2025 | 49.8% | measured |
| ARC-AGI-1 | 50.1% | estimated ± 7.6 pp, low confidence |
| ARC-AGI-2 | 30.7% | estimated ± 14.6 pp, low confidence |
| ParseBench | 43.5% | estimated ± 5.5 pp, medium 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 | 28.5% | estimated ± 4.6 pp, medium confidence |
| ARC-AGI-3 | 1.4% | estimated ± 7.7 pp, low confidence |
| CharXiv | 65.5% | estimated ± 6.2 pp, low confidence |
| AI2D_TEST | 89.1% | estimated ± 2.0 pp, high confidence |
| C-Eval | 87.6% | estimated ± 1.0 pp, low confidence |
| CountBench | 94.5% | estimated ± 3.2 pp, high confidence |
| DynaMath | 82.3% | estimated ± 5.8 pp, low confidence |
| ERQA | 47.1% | estimated ± 5.2 pp, low confidence |
| MathVision | 71.5% | estimated ± 3.6 pp, high confidence |
| MLVU (M-Avg) | 82.8% | estimated ± 2.4 pp, high confidence |
| MMLU-Redux | 92.9% | estimated ± 0.8 pp, low confidence |
| MMMU-Pro | 54.6% | estimated ± 1.6 pp, high confidence |
| RealWorldQA | 80.0% | estimated ± 3.6 pp, high confidence |
| ScreenSpot Pro | 53.0% | estimated ± 7.3 pp, low confidence |
| SimpleVQA | 54.4% | estimated ± 7.1 pp, medium confidence |
| SuperGPQA | 45.4% | estimated ± 8.2 pp, low confidence |
| Video-MME (w/o subtitle) | 74.1% | estimated ± 1.3 pp, high confidence |
| Video-MME (with subtitle) | 79.8% | estimated ± 3.2 pp, high confidence |
| VideoMMMU | 67.1% | estimated ± 3.8 pp, high confidence |
| We-Math | 76.3% | estimated ± 7.2 pp, low confidence |
| HealthBench Hard | 0.0% | estimated ± 8.6 pp, low confidence |
| MMLU-Pro (Arcee) | 77.1% | estimated ± 4.0 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.3 pp, medium confidence |
| HealthBench Professional (raw) | 49.0% | estimated ± 8.6 pp, low confidence |
| STEMBench | 2.4% | estimated ± 0.2 pp, medium confidence |
| SimpleQA | 10.7% | measured |
| LiveCodeBench | 41.2% | estimated ± 14.6 pp, low confidence |
| MMVU | 68.4% | estimated ± 3.8 pp, medium confidence |
| MRCRv2 | 22.8% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 56.7% | estimated ± 2.6 pp, low confidence |
| MMMU-Pro w/ Python | 59.3% | estimated ± 2.0 pp, medium confidence |