Other · model
Gemma 4 E2B benchmark scores
As of 2026-11-21, Gemma 4 E2B (Other) has measured scores on 14 benchmarks and estimated scores on 84 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 43.3% | measured |
| AA-HLE | 4.8% | measured |
| AA-SciCode | 25.5% | estimated ± 3.4 pp, medium confidence |
| Artificial Analysis Intelligence Index | 12.6% | estimated ± 7.2 pp, medium confidence |
| CritPt | 0.0% | measured |
| GDPval-AA | 0.0% | measured |
| GPQA Diamond | 43.9% | estimated ± 1.2 pp, high confidence |
| HLE | 1.0% | estimated ± 6.5 pp, low confidence |
| IFBench | 54.0% | estimated ± 6.6 pp, low confidence |
| AA-LCR | 16.3% | measured |
| LiveCodeBench v6 | 44.0% | measured |
| AA-Omniscience Accuracy | 18.5% | estimated ± 7.7 pp, medium confidence |
| SciCode | 26.4% | estimated ± 4.6 pp, medium confidence |
| BrowseComp | 0.0% | estimated ± 9.2 pp, low confidence |
| HLE w/ tools | 33.8% | estimated ± 5.3 pp, low confidence |
| IFEval | 88.2% | estimated ± 2.8 pp, high confidence |
| LongBench v2 | 51.2% | estimated ± 5.5 pp, low confidence |
| τ²-bench results | 20.8% | measured |
| AA Coding Index | 7.2% | measured |
| AA-MMMU-Pro | 44.6% | measured |
| APEX-Agents | 0.0% | estimated ± 9.4 pp, low confidence |
| APEX-Agents-AA | 6.0% | estimated ± 9.5 pp, medium confidence |
| BioMysteryBench (human-difficult) | 0.0% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 34.7% | estimated ± 9.6 pp, medium confidence |
| SWE-bench Verified | 19.4% | estimated ± 6.5 pp, low confidence |
| BFCL v4 | 53.9% | estimated ± 2.7 pp, high confidence |
| CyberGym | 0.0% | estimated ± 6.0 pp, low confidence |
| JobBench | 0.0% | estimated ± 8.7 pp, low confidence |
| SWE-bench Pro | 11.1% | estimated ± 6.0 pp, low confidence |
| WideResearch | 0.0% | estimated ± 7.8 pp, low confidence |
| AA Agentic Index | 0.0% | estimated ± 3.1 pp, high confidence |
| MMLU-Pro | 60.0% | measured |
| AA-IFBench | 38.0% | measured |
| BBH | 82.6% | estimated ± 2.8 pp, high confidence |
| GPQA | 43.4% | measured |
| MMLU | 79.0% | estimated ± 2.1 pp, high confidence |
| Vals GPQA Diamond | 42.5% | estimated ± 3.2 pp, high confidence |
| Vals LiveCodeBench | 27.8% | estimated ± 7.1 pp, low confidence |
| Vals MMLU-Pro | 63.5% | estimated ± 2.3 pp, high confidence |
| MMMLU | 83.3% | estimated ± 0.7 pp, medium confidence |
| MMMU | 59.0% | estimated ± 1.7 pp, high confidence |
| AA MMLU-Pro | 85.7% | estimated ± 1.3 pp, medium confidence |
| Gert Labs | 32.2% | estimated ± 8.5 pp, medium confidence |
| AA Tau3 Banking | 0.0% | estimated ± 4.1 pp, medium confidence |
| ARC-AGI-1 | 74.7% | estimated ± 7.8 pp, low confidence |
| ARC-AGI-2 | 30.5% | estimated ± 14.4 pp, low confidence |
| MazeBench | 0.4% | estimated ± 5.5 pp, low confidence |
| OSWorld-Verified | 55.4% | estimated ± 8.4 pp, low confidence |
| ParseBench-1 | 41.3% | estimated ± 6.2 pp, low confidence |
| Vals SWE-bench | 29.0% | estimated ± 5.5 pp, low confidence |
| CWE-Bench-AA | 0.0% | estimated ± 10.1 pp, low confidence |
| DeepsecBench-AA | 0.0% | estimated ± 8.9 pp, low confidence |
| AA ITBench | 35.7% | estimated ± 5.1 pp, low confidence |
| CWE-bench v1 | 0.0% | estimated ± 6.4 pp, low confidence |
| DRACO | 0.0% | estimated ± 2.0 pp, low confidence |
| HLE w/o tools | 3.2% | estimated ± 5.4 pp, low confidence |
| Toolathlon-Verified | 0.0% | estimated ± 3.1 pp, medium confidence |
| GDP.pdf | 17.0% | estimated ± 4.6 pp, medium confidence |
| ARC-AGI-3 | 1.3% | estimated ± 9.8 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| Vibe Code Bench | 1.7% | estimated ± 10.0 pp, low confidence |
| Hermes Bench | 0.0% | estimated ± 2.9 pp, medium confidence |
| Hermes Index | 0.0% | estimated ± 8.7 pp, low confidence |
| ParseBench-2 | 30.7% | estimated ± 5.0 pp, low confidence |
| CharXiv | 35.7% | estimated ± 5.6 pp, low confidence |
| CharXiv w/o tools | 70.1% | estimated ± 1.2 pp, medium confidence |
| AI2D_TEST | 88.0% | estimated ± 2.0 pp, low confidence |
| C-Eval | 90.8% | estimated ± 1.1 pp, low confidence |
| CountBench | 91.3% | estimated ± 3.0 pp, high confidence |
| DynaMath | 78.1% | estimated ± 5.3 pp, low confidence |
| ERQA | 47.4% | estimated ± 6.4 pp, low confidence |
| MathVision | 49.8% | estimated ± 3.0 pp, medium confidence |
| MCP Atlas | 56.5% | estimated ± 10.7 pp, low confidence |
| MLVU (M-Avg) | 70.7% | estimated ± 2.2 pp, medium confidence |
| MMLU-Redux | 77.5% | estimated ± 0.6 pp, high confidence |
| MMMU-Pro | 44.2% | measured |
| QwenClawBench | 55.9% | estimated ± 6.0 pp, low confidence |
| RealWorldQA | 76.5% | estimated ± 2.8 pp, high confidence |
| ScreenSpot Pro | 51.0% | estimated ± 9.6 pp, low confidence |
| SimpleVQA | 37.4% | estimated ± 7.5 pp, medium confidence |
| SuperGPQA | 38.6% | estimated ± 12.4 pp, low confidence |
| Toolathlon | 27.0% | estimated ± 6.3 pp, low confidence |
| Video-MME (w/o subtitle) | 61.7% | estimated ± 1.3 pp, medium confidence |
| Video-MME (with subtitle) | 66.5% | estimated ± 3.0 pp, medium confidence |
| VideoMMMU | 47.8% | estimated ± 2.4 pp, medium confidence |
| We-Math | 65.8% | estimated ± 7.4 pp, low confidence |
| HealthBench Hard | 0.0% | estimated ± 8.6 pp, low confidence |
| MMLU-Pro (Arcee) | 77.1% | estimated ± 4.0 pp, low confidence |
| React Native Evals | 65.8% | estimated ± 3.2 pp, medium confidence |
| ResearchClawBench | 11.1% | estimated ± 2.2 pp, low confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| ScarfBench | 24.4% | estimated ± 9.1 pp, low confidence |
| SimpleQA | 10.1% | estimated ± 7.8 pp, low confidence |
| MMVU | 52.5% | estimated ± 2.7 pp, low confidence |
| MRCRv2 | 19.1% | measured |
| MMLongBench-Doc | 50.5% | estimated ± 2.6 pp, low confidence |
| OCRBench V2 | 58.2% | estimated ± 3.3 pp, high confidence |
| BioBasicsBench | 33.9% | estimated ± 10.7 pp, low confidence |