Other · model
Hy4 preview benchmark scores
As of 2026-10-07, Hy4 preview (Other) has measured scores on 25 benchmarks and estimated scores on 69 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 90.9% | estimated ± 2.7 pp, high confidence |
| AA-HLE | 41.5% | estimated ± 4.0 pp, high confidence |
| AA-SciCode | 52.7% | estimated ± 3.0 pp, high confidence |
| Artificial Analysis Intelligence Index | 40.4% | estimated ± 5.1 pp, medium confidence |
| CritPt | 16.9% | measured |
| GDPval-AA | 25.4% | estimated ± 3.7 pp, low confidence |
| GPQA Diamond | 92.3% | measured |
| HLE | 55.4% | measured |
| LiveCodeBench v6 | 92.1% | estimated ± 2.1 pp, high confidence |
| AA-Omniscience Accuracy | 45.0% | estimated ± 7.9 pp, medium confidence |
| SciCode | 54.1% | estimated ± 4.8 pp, high confidence |
| Terminal-Bench 2.1 | 85.4% | measured |
| BrowseComp | 83.3% | estimated ± 5.2 pp, low confidence |
| HLE w/ tools | 55.4% | measured |
| VITA-Bench | 49.6% | estimated ± 9.9 pp, low confidence |
| AA Coding Index | 74.4% | estimated ± 2.5 pp, high confidence |
| AA-MMMU-Pro | 83.7% | estimated ± 2.9 pp, high confidence |
| APEX-Agents | 37.1% | measured |
| APEX-Agents-AA | 41.7% | estimated ± 3.6 pp, low confidence |
| BioMysteryBench (human-difficult) | 47.2% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 90.2% | estimated ± 10.9 pp, low confidence |
| SWE-bench Verified | 82.9% | estimated ± 2.4 pp, high confidence |
| AutomationBench | 32.1% | measured |
| CyberGym | 78.4% | measured |
| JobBench | 61.7% | measured |
| SkillsBench | 62.9% | measured |
| SWE-bench Pro | 65.7% | measured |
| τ³-bench results | 69.6% | estimated ± 1.8 pp, low confidence |
| WideResearch | 83.9% | measured |
| AA Agentic Index | 50.6% | estimated ± 3.3 pp, medium confidence |
| MMLU-Pro | 85.7% | estimated ± 2.5 pp, low confidence |
| GPQA | 92.3% | measured |
| Gert Labs | 67.4% | estimated ± 6.0 pp, low confidence |
| AA-AnalystAgent | 48.4% | estimated ± 2.5 pp, medium confidence |
| AA EnterpriseOps-Gym | 48.3% | estimated ± 5.1 pp, low confidence |
| AA Harvey LAB | 89.6% | estimated ± 1.7 pp, medium confidence |
| ApprenticeBench | 8.8% | estimated ± 4.0 pp, medium confidence |
| ARC-AGI-1 | 92.4% | estimated ± 2.7 pp, high confidence |
| ARC-AGI-2 | 67.1% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 58.3% | estimated ± 5.6 pp, low confidence |
| CursorBench 3.2 | 64.2% | estimated ± 3.6 pp, high confidence |
| Terminal-Bench 3.0 | 3.5% | estimated ± 6.9 pp, low confidence |
| FrontierCode 1.1 Main | 43.0% | estimated ± 3.7 pp, low confidence |
| FrontierSWE v2 | 25.3% | estimated ± 9.0 pp, medium confidence |
| OfficeQA Pro | 66.2% | measured |
| OSWorld-Verified | 78.6% | estimated ± 4.7 pp, high confidence |
| Vals GPQA Diamond | 91.6% | estimated ± 2.0 pp, high confidence |
| Vals LiveCodeBench | 86.7% | estimated ± 4.7 pp, medium confidence |
| Vals MMLU-Pro | 87.9% | estimated ± 1.2 pp, high confidence |
| Vals SWE-bench | 92.1% | estimated ± 5.4 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 55.1% | measured |
| AA AutomationBench | 56.8% | estimated ± 5.0 pp, medium confidence |
| GDP.pdf | 11.6% | estimated ± 3.4 pp, medium confidence |
| AA ITBench | 51.4% | estimated ± 3.4 pp, medium confidence |
| AA Tau3 Banking | 47.4% | estimated ± 10.7 pp, low confidence |
| AA Terminal-Bench 2.1 | 84.9% | estimated ± 3.5 pp, high confidence |
| AA Terminal-Bench 4.0 | 25.2% | estimated ± 8.9 pp, medium confidence |
| CursorBench 4.0 | 39.8% | estimated ± 3.6 pp, high confidence |
| CWE-bench v1 | 53.0% | measured |
| DeepSWE | 64.3% | measured |
| HLE w/o tools | 43.4% | measured |
| OSWorld 2.0 | 19.4% | estimated ± 5.5 pp, low confidence |
| PostTrainBench v1.1 | 29.3% | estimated ± 4.7 pp, high confidence |
| ProgramBench | 17.5% | measured |
| SWE Multilingual | 82.9% | measured |
| Toolathlon-Verified | 74.1% | measured |
| ExploitGym | 9.7% | estimated ± 9.3 pp, low confidence |
| C-Eval | 93.3% | estimated ± 0.8 pp, low confidence |
| Claw-Eval | 66.2% | estimated ± 5.6 pp, low confidence |
| DeepPlanning | 51.8% | estimated ± 13.1 pp, low confidence |
| MCP Atlas | 83.7% | measured |
| MCP-Tasks | 77.1% | estimated ± 0.6 pp, low confidence |
| MMLU-ProX | 87.7% | estimated ± 1.7 pp, low confidence |
| MMLU-Redux | 96.9% | estimated ± 2.1 pp, low confidence |
| NL2Repo | 58.9% | measured |
| NOVA-63 | 60.4% | estimated ± 1.6 pp, low confidence |
| QwenClawBench | 69.0% | estimated ± 2.6 pp, medium confidence |
| SuperGPQA | 84.8% | estimated ± 9.1 pp, low confidence |
| Terminal-Bench 2.0 | 62.8% | estimated ± 5.9 pp, medium confidence |
| Toolathlon | 52.5% | estimated ± 5.2 pp, low confidence |
| HealthBench Hard | 31.2% | estimated ± 5.1 pp, low confidence |
| LiveCodeBench Pro | 88.0% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (Text) | 61.3% | estimated ± 4.5 pp, medium confidence |
| MMLU-Pro (Arcee) | 87.6% | estimated ± 3.4 pp, low confidence |
| ResearchClawBench | 19.5% | estimated ± 1.8 pp, low confidence |
| ARC-AGI-3 | 0.1% | estimated ± 2.1 pp, high confidence |
| BioMysteryBench (human-solvable) | 88.4% | estimated ± 0.6 pp, medium confidence |
| DRACO | 77.2% | measured |
| FrontierCode 1.1 Extended | 57.8% | estimated ± 3.0 pp, medium confidence |
| HealthBench Professional | 54.6% | estimated ± 4.8 pp, medium confidence |
| Agents' Last Exam | 22.8% | measured |
| OpenHarmony Bench | 59.1% | estimated ± 2.7 pp, high confidence |
| MMMLU | 90.6% | estimated ± 1.1 pp, medium confidence |
| MMLU | 90.4% | estimated ± 3.6 pp, low confidence |