Other · model
Gemma 4 26B A4B benchmark scores
As of 2026-10-07, Gemma 4 26B A4B (Other) has measured scores on 16 benchmarks and estimated scores on 85 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 79.2% | measured |
| AA-HLE | 19.3% | measured |
| AA-SciCode | 40.0% | measured |
| Artificial Analysis Intelligence Index | 16.7% | measured |
| CritPt | 0.0% | measured |
| GDPval-AA | 3.4% | measured |
| GPQA Diamond | 79.7% | estimated ± 1.9 pp, high confidence |
| HLE | 17.2% | measured |
| IFBench | 70.9% | estimated ± 6.9 pp, medium confidence |
| AA-LCR | 65.7% | measured |
| LiveCodeBench v6 | 81.0% | estimated ± 3.1 pp, high confidence |
| AA-Omniscience Accuracy | 19.1% | measured |
| SciCode | 40.0% | estimated ± 3.2 pp, high confidence |
| BrowseComp | 19.8% | estimated ± 10.1 pp, low confidence |
| HLE w/ tools | 33.3% | estimated ± 6.1 pp, low confidence |
| IFEval | 93.5% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, medium confidence |
| τ²-bench results | 43.6% | measured |
| AA Coding Index | 39.3% | measured |
| AA-MMMU-Pro | 69.2% | measured |
| APEX-Agents | 3.5% | estimated ± 10.0 pp, low confidence |
| APEX-Agents-AA | 6.9% | estimated ± 9.1 pp, medium confidence |
| BioMysteryBench (human-difficult) | 26.2% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 44.0% | estimated ± 8.4 pp, medium confidence |
| SWE-bench Verified | 67.7% | estimated ± 5.5 pp, medium confidence |
| AutomationBench | 28.4% | estimated ± 9.7 pp, low confidence |
| BFCL v4 | 61.0% | estimated ± 2.6 pp, high confidence |
| CyberGym | 9.2% | estimated ± 6.2 pp, low confidence |
| JobBench | 0.0% | estimated ± 8.6 pp, low confidence |
| SWE-bench Pro | 44.6% | estimated ± 6.0 pp, medium confidence |
| WideResearch | 47.0% | estimated ± 9.1 pp, low confidence |
| AA Agentic Index | 3.2% | estimated ± 2.8 pp, high confidence |
| MMLU-Pro | 82.6% | measured |
| GPQA | 80.2% | estimated ± 2.1 pp, high confidence |
| AA-IFBench | 72.4% | measured |
| Gert Labs | 36.2% | estimated ± 8.9 pp, medium confidence |
| AA-AnalystAgent | 2.1% | estimated ± 12.0 pp, low confidence |
| AA EnterpriseOps-Gym | 1.8% | estimated ± 3.6 pp, low confidence |
| ARC-AGI-1 | 14.8% | estimated ± 3.7 pp, medium confidence |
| ARC-AGI-2 | 0.0% | estimated ± 13.0 pp, low confidence |
| CursorBench 3.1 | 19.3% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 25.4% | estimated ± 4.4 pp, medium confidence |
| FrontierCode 1.1 Main | 14.6% | estimated ± 3.8 pp, medium confidence |
| FrontierSWE v2 | 0.0% | estimated ± 14.6 pp, low confidence |
| OfficeQA Pro | 50.3% | estimated ± 7.2 pp, low confidence |
| OSWorld-Verified | 57.3% | estimated ± 8.7 pp, low confidence |
| Vals GPQA Diamond | 57.2% | estimated ± 3.0 pp, medium confidence |
| Vals MMLU-Pro | 61.2% | estimated ± 1.9 pp, medium confidence |
| Vals SWE-bench | 62.4% | estimated ± 5.4 pp, medium confidence |
| AA AutomationBench | 3.7% | estimated ± 7.0 pp, low confidence |
| GDP.pdf | 9.4% | estimated ± 5.4 pp, low confidence |
| AA ITBench | 97.1% | estimated ± 3.6 pp, low confidence |
| AA Tau3 Banking | 22.0% | estimated ± 5.8 pp, low confidence |
| CursorBench 4.0 | 10.8% | estimated ± 1.6 pp, medium confidence |
| CWE-bench v1 | 6.1% | estimated ± 6.9 pp, low confidence |
| DeepSWE | 3.7% | estimated ± 6.4 pp, low confidence |
| HLE w/o tools | 8.7% | measured |
| PostTrainBench v1.1 | 8.9% | estimated ± 6.1 pp, low confidence |
| Toolathlon-Verified | 10.3% | estimated ± 2.4 pp, medium confidence |
| Vibe Code Bench | 14.4% | estimated ± 10.3 pp, low confidence |
| CharXiv | 75.3% | estimated ± 5.4 pp, medium confidence |
| CharXiv w/o tools | 77.7% | estimated ± 1.8 pp, medium confidence |
| C-Eval | 82.1% | estimated ± 0.8 pp, low confidence |
| MathVision | 78.8% | estimated ± 3.6 pp, high confidence |
| MCP Atlas | 52.2% | estimated ± 11.1 pp, low confidence |
| MCP-Tasks | 99.0% | estimated ± 8.2 pp, low confidence |
| MMLU-Redux | 91.7% | estimated ± 0.7 pp, high confidence |
| MMMU-Pro | 73.8% | measured |
| NL2Repo | 27.8% | estimated ± 5.1 pp, low confidence |
| QwenClawBench | 55.9% | estimated ± 6.0 pp, low confidence |
| ScreenSpot Pro | 63.3% | estimated ± 10.0 pp, low confidence |
| SuperGPQA | 62.9% | estimated ± 7.5 pp, medium confidence |
| Toolathlon | 26.9% | estimated ± 6.3 pp, low confidence |
| VideoMMMU | 84.1% | estimated ± 1.0 pp, high confidence |
| ERQA | 25.0% | estimated ± 3.9 pp, medium confidence |
| HealthBench Hard | 2.9% | estimated ± 7.7 pp, low confidence |
| MedXpertQA (MM) | 60.3% | estimated ± 2.4 pp, high confidence |
| MedXpertQA (Text) | 16.1% | estimated ± 8.9 pp, low confidence |
| MMLU-Pro (Arcee) | 77.1% | estimated ± 4.0 pp, low confidence |
| React Native Evals | 74.0% | estimated ± 3.5 pp, high confidence |
| ResearchClawBench | 5.2% | estimated ± 2.2 pp, low confidence |
| SWE-Rebench | 0.0% | estimated ± 8.9 pp, low confidence |
| ARC-AGI-3 | 1.7% | estimated ± 3.4 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| DRACO | 62.9% | estimated ± 3.0 pp, low confidence |
| FrontierCode 1.1 Extended | 36.3% | estimated ± 3.4 pp, low confidence |
| HealthBench (raw) | 27.1% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 13.7% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 39.3% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 61.7% | estimated ± 1.8 pp, low confidence |
| MMMU | 78.6% | estimated ± 0.9 pp, high confidence |
| LiveCodeBench | 72.3% | estimated ± 8.9 pp, low confidence |
| OpenHarmony Bench | 51.0% | estimated ± 2.4 pp, medium confidence |
| SimpleVQA | 64.5% | estimated ± 8.2 pp, medium confidence |
| MMLU | 85.6% | estimated ± 1.1 pp, medium confidence |
| MMMU-Pro w/ Python | 75.4% | estimated ± 0.6 pp, high confidence |
| RealWorldQA | 81.6% | estimated ± 1.2 pp, low confidence |
| Video-MME (with subtitle) | 85.8% | estimated ± 1.8 pp, low confidence |
| OmniDocBench 1.5 | 70.5% | estimated ± 5.9 pp, low confidence |