Other · model
Gemma 4 E4B benchmark scores
As of 2026-11-22, Gemma 4 E4B (Other) has measured scores on 19 benchmarks and estimated scores on 85 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 57.6% | measured |
| AA-HLE | 3.8% | measured |
| AA-SciCode | 24.4% | measured |
| Artificial Analysis Intelligence Index | 4.8% | measured |
| CritPt | 0.6% | measured |
| GDPval-AA | 0.0% | measured |
| GPQA Diamond | 58.9% | estimated ± 1.2 pp, high confidence |
| HLE | 4.4% | estimated ± 6.5 pp, low confidence |
| IFBench | 54.7% | estimated ± 6.6 pp, medium confidence |
| AA-LCR | 32.0% | measured |
| LiveCodeBench v6 | 52.0% | measured |
| AA-Omniscience Accuracy | 9.7% | measured |
| SciCode | 25.0% | estimated ± 3.1 pp, medium confidence |
| BrowseComp | 0.0% | estimated ± 9.2 pp, low confidence |
| HLE w/ tools | 33.8% | estimated ± 5.3 pp, low confidence |
| IFEval | 90.0% | estimated ± 2.8 pp, high confidence |
| LongBench v2 | 51.2% | estimated ± 5.5 pp, medium confidence |
| τ²-bench results | 20.8% | measured |
| AA Coding Index | 9.4% | measured |
| AA-MMMU-Pro | 51.4% | 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) | 11.6% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 34.7% | estimated ± 9.6 pp, medium confidence |
| SWE-bench Verified | 43.4% | estimated ± 6.3 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 | 0.0% | 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 | 69.4% | measured |
| AA-IFBench | 44.2% | measured |
| BBH | 89.2% | estimated ± 2.8 pp, medium confidence |
| GPQA | 58.6% | measured |
| MMLU | 80.3% | estimated ± 0.9 pp, medium confidence |
| Vals GPQA Diamond | 56.7% | estimated ± 3.2 pp, high confidence |
| Vals LiveCodeBench | 60.9% | estimated ± 5.7 pp, low confidence |
| Vals MMLU-Pro | 73.3% | estimated ± 2.3 pp, high confidence |
| MMMLU | 85.9% | estimated ± 0.7 pp, medium confidence |
| MMMU | 65.9% | estimated ± 0.8 pp, medium confidence |
| AA MMLU-Pro | 82.5% | estimated ± 0.8 pp, medium confidence |
| Gert Labs | 26.9% | estimated ± 10.0 pp, low confidence |
| AA Tau3 Banking | 0.0% | estimated ± 4.1 pp, medium confidence |
| ARC-AGI-1 | 75.2% | estimated ± 7.8 pp, low confidence |
| ARC-AGI-2 | 31.7% | 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 | 41.1% | measured |
| Vals SWE-bench | 31.7% | 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 |
| HealthBench Professional (raw, Artificial Analysis) | 0.4% | estimated ± 2.5 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 | 19.7% | estimated ± 4.9 pp, high 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 | 2.2% | 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 | 42.8% | measured |
| CharXiv | 76.8% | estimated ± 5.6 pp, low confidence |
| CharXiv w/o tools | 70.7% | estimated ± 1.2 pp, high confidence |
| AI2D_TEST | 88.0% | estimated ± 2.0 pp, low confidence |
| C-Eval | 87.0% | estimated ± 1.0 pp, low confidence |
| CountBench | 92.6% | estimated ± 3.0 pp, high confidence |
| DynaMath | 79.8% | estimated ± 5.3 pp, low confidence |
| ERQA | 47.4% | estimated ± 6.4 pp, medium confidence |
| MathVision | 59.1% | estimated ± 3.0 pp, high confidence |
| MCP Atlas | 56.5% | estimated ± 10.7 pp, low confidence |
| MLVU (M-Avg) | 74.5% | estimated ± 2.2 pp, high confidence |
| MMLU-Redux | 83.8% | estimated ± 0.6 pp, high confidence |
| MMMU-Pro | 52.6% | measured |
| NL2Repo | 3.1% | estimated ± 4.7 pp, medium confidence |
| QwenClawBench | 55.9% | estimated ± 6.0 pp, low confidence |
| RealWorldQA | 78.3% | estimated ± 2.8 pp, high confidence |
| ScreenSpot Pro | 57.9% | estimated ± 9.6 pp, low confidence |
| SimpleVQA | 41.5% | estimated ± 7.5 pp, medium confidence |
| SuperGPQA | 40.8% | estimated ± 8.5 pp, low confidence |
| Toolathlon | 27.0% | estimated ± 6.3 pp, low confidence |
| Video-MME (w/o subtitle) | 68.5% | estimated ± 1.3 pp, high confidence |
| Video-MME (with subtitle) | 72.8% | estimated ± 3.0 pp, high confidence |
| VideoMMMU | 58.9% | estimated ± 2.4 pp, high confidence |
| We-Math | 70.2% | estimated ± 7.4 pp, low confidence |
| HealthBench Hard | 6.5% | estimated ± 8.6 pp, low confidence |
| MMLU-Pro (Arcee) | 79.4% | estimated ± 4.0 pp, medium confidence |
| React Native Evals | 66.4% | 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 |
| HealthBench (length-adjusted) | 54.1% | estimated ± 3.7 pp, medium confidence |
| HealthBench Professional | 56.7% | estimated ± 4.2 pp, low confidence |
| ScarfBench | 24.4% | estimated ± 9.1 pp, low confidence |
| STEMBench | 2.2% | estimated ± 0.2 pp, low confidence |
| SimpleQA | 4.0% | estimated ± 4.3 pp, low confidence |
| MMVU | 59.5% | estimated ± 2.7 pp, medium confidence |
| MRCRv2 | 25.4% | measured |
| MMLongBench-Doc | 56.7% | estimated ± 2.6 pp, low confidence |
| OCRBench V2 | 62.4% | estimated ± 3.3 pp, high confidence |
| BioBasicsBench | 6.2% | estimated ± 10.2 pp, low confidence |
| MMMU-Pro w/ Python | 57.0% | estimated ± 2.0 pp, medium confidence |