Other · model
Hy3 Preview benchmark scores
As of 2026-11-21, Hy3 Preview (Other) has measured scores on 19 benchmarks and estimated scores on 100 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 89.7% | measured |
| AA-HLE | 33.5% | measured |
| AA-SciCode | 48.6% | measured |
| Artificial Analysis Intelligence Index | 41.2% | measured |
| CritPt | 4.9% | measured |
| GDPval-AA | 35.8% | measured |
| GPQA Diamond | 87.2% | measured |
| HLE | 25.5% | measured |
| IFBench | 63.1% | measured |
| AA-LCR | 66.7% | measured |
| LiveCodeBench v6 | 80.8% | estimated ± 4.4 pp, high confidence |
| AA-Omniscience Accuracy | 31.5% | measured |
| SciCode | 41.2% | measured |
| BrowseComp | 59.4% | estimated ± 6.6 pp, medium confidence |
| HLE w/ tools | 51.1% | estimated ± 5.3 pp, medium confidence |
| IFEval | 90.1% | estimated ± 3.6 pp, high confidence |
| LongBench v2 | 56.8% | estimated ± 5.5 pp, medium confidence |
| AA Coding Index | 58.8% | measured |
| APEX-Agents | 27.8% | estimated ± 9.4 pp, low confidence |
| APEX-Agents-AA | 28.2% | estimated ± 9.5 pp, medium confidence |
| BioMysteryBench (human-difficult) | 37.0% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 87.4% | estimated ± 4.5 pp, high confidence |
| SWE-bench Verified | 74.4% | measured |
| BFCL v4 | 75.2% | estimated ± 2.7 pp, medium confidence |
| CyberGym | 65.3% | estimated ± 5.3 pp, medium confidence |
| JobBench | 35.6% | estimated ± 8.7 pp, medium confidence |
| SWE-bench Pro | 52.3% | estimated ± 4.5 pp, high confidence |
| WideResearch | 49.7% | estimated ± 5.9 pp, low confidence |
| AA Agentic Index | 25.6% | measured |
| MMLU-Pro | 84.5% | estimated ± 4.4 pp, high confidence |
| AA-IFBench | 56.7% | estimated ± 7.4 pp, medium confidence |
| FailureSensorIQ | 62.7% | estimated ± 1.7 pp, high confidence |
| GPQA | 87.2% | measured |
| MMLU | 90.5% | estimated ± 0.9 pp, high confidence |
| Vals GPQA Diamond | 86.5% | estimated ± 2.1 pp, high confidence |
| Vals LiveCodeBench | 84.2% | estimated ± 0.8 pp, low confidence |
| Vals MMLU-Pro | 85.1% | estimated ± 1.6 pp, high confidence |
| MMMLU | 88.4% | estimated ± 0.7 pp, medium confidence |
| Chess Puzzles | 19.3% | estimated ± 12.3 pp, low confidence |
| AA MMLU-Pro | 85.9% | estimated ± 0.8 pp, high confidence |
| Gert Labs | 36.9% | measured |
| AA Harvey LAB v1.0 | 84.3% | estimated ± 1.2 pp, medium confidence |
| AA Tau3 Banking | 30.7% | estimated ± 3.7 pp, high confidence |
| ARC-AGI-1 | 84.8% | estimated ± 2.5 pp, medium confidence |
| ARC-AGI-2 | 41.7% | estimated ± 9.7 pp, low confidence |
| CursorBench 3.1 | 40.6% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 43.9% | estimated ± 4.4 pp, medium confidence |
| FrontierCode 1.1 Main | 17.6% | estimated ± 4.2 pp, low confidence |
| FrontierSWE v2 | 15.9% | estimated ± 14.2 pp, low confidence |
| MazeBench | 0.4% | estimated ± 5.5 pp, low confidence |
| Mystery Game Puzzles | 13.5% | estimated ± 14.6 pp, low confidence |
| NYT Connections | 17.2% | measured |
| OSWorld-Verified | 54.8% | estimated ± 5.5 pp, medium confidence |
| Terminal-Bench Hard | 43.1% | estimated ± 4.0 pp, medium confidence |
| Vals SWE-bench | 65.9% | estimated ± 5.3 pp, low confidence |
| Terminal-Bench 2.1 (Vals AI) | 47.8% | estimated ± 6.4 pp, medium confidence |
| CWE-Bench-AA | 42.6% | estimated ± 10.1 pp, low confidence |
| AA Cyber Index | 16.8% | estimated ± 9.2 pp, low confidence |
| DeepsecBench-AA | 8.4% | estimated ± 8.9 pp, low confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 58.4% | estimated ± 4.3 pp, medium confidence |
| HealthBench Professional (raw, Artificial Analysis) | 41.4% | estimated ± 0.8 pp, low confidence |
| AA ITBench | 36.2% | estimated ± 2.8 pp, high confidence |
| Bug Hunt Bench | 7.5% | estimated ± 9.0 pp, low confidence |
| CursorBench 4.0 | 34.9% | estimated ± 4.9 pp, medium confidence |
| CWE-bench v1 | 44.7% | estimated ± 6.4 pp, medium confidence |
| DeepSWE | 30.4% | estimated ± 6.4 pp, low confidence |
| DRACO | 79.1% | estimated ± 2.0 pp, medium confidence |
| FrontierCode 2.0 | 26.1% | estimated ± 9.3 pp, low confidence |
| HLE w/o tools | 39.2% | estimated ± 2.7 pp, medium confidence |
| OSWorld 2.1 | 52.0% | estimated ± 6.0 pp, low confidence |
| OSWorld 2.1 Offline | 17.5% | estimated ± 1.9 pp, low confidence |
| PostTrainBench v1.1 | 14.6% | estimated ± 5.7 pp, low confidence |
| StealthMark | 41.3% | estimated ± 10.7 pp, low confidence |
| Toolathlon-Verified | 55.3% | estimated ± 2.3 pp, medium confidence |
| VulcanBench Frontier v4 | 78.8% | estimated ± 6.8 pp, low confidence |
| GDP.pdf | 17.0% | estimated ± 4.6 pp, high confidence |
| ARC-AGI-3 | 0.0% | estimated ± 8.6 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, low confidence |
| cursorBench41 | 44.8% | estimated ± 3.7 pp, medium confidence |
| MKA | 29.0% | estimated ± 6.4 pp, low confidence |
| SkillsBench official leaderboard (BenchFlow) | 30.8% | estimated ± 6.1 pp, medium confidence |
| BinaryAudit | 9.9% | estimated ± 12.1 pp, low confidence |
| OTelBench | 6.8% | estimated ± 6.6 pp, medium confidence |
| Vibe Code Bench | 1.5% | estimated ± 8.4 pp, medium confidence |
| Hermes Bench | 63.6% | estimated ± 2.9 pp, high confidence |
| Hermes Index | 31.3% | estimated ± 8.7 pp, medium confidence |
| ExploitGym | 6.3% | estimated ± 10.6 pp, low confidence |
| C-Eval | 91.9% | estimated ± 0.9 pp, medium confidence |
| Claw-Eval | 53.6% | estimated ± 6.8 pp, low confidence |
| MCP Atlas | 78.3% | estimated ± 7.8 pp, low confidence |
| MMLU-Redux | 94.9% | estimated ± 0.8 pp, medium confidence |
| NL2Repo | 42.7% | estimated ± 4.7 pp, high confidence |
| PostTrainBench v1 | 13.4% | estimated ± 5.5 pp, low confidence |
| QwenClawBench | 93.1% | estimated ± 6.0 pp, low confidence |
| SuperGPQA | 66.2% | estimated ± 7.2 pp, medium confidence |
| Terminal-Bench 2.0 | 54.4% | measured |
| Toolathlon | 55.8% | estimated ± 6.3 pp, medium confidence |
| AA LiveCodeBench | 88.1% | estimated ± 4.7 pp, low confidence |
| HealthBench Hard | 0.0% | estimated ± 5.1 pp, low confidence |
| MedXpertQA (Text) | 46.4% | estimated ± 4.5 pp, low confidence |
| MMLU-Pro (Arcee) | 85.9% | estimated ± 3.4 pp, medium confidence |
| React Native Evals | 77.1% | estimated ± 2.7 pp, medium confidence |
| ResearchClawBench | 17.9% | estimated ± 1.9 pp, high confidence |
| SWE-Rebench | 57.1% | estimated ± 3.6 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.8% | estimated ± 0.6 pp, low confidence |
| HealthBench (raw) | 42.5% | estimated ± 6.0 pp, low confidence |
| HealthBench (length-adjusted) | 51.1% | estimated ± 3.4 pp, low confidence |
| HealthBench Professional | 58.1% | estimated ± 4.2 pp, medium confidence |
| HealthBench Professional (raw) | 53.5% | estimated ± 4.5 pp, medium confidence |
| HLE-Verified | 16.8% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 76.6% | estimated ± 1.8 pp, low confidence |
| ScarfBench | 25.9% | estimated ± 9.1 pp, low confidence |
| STEMBench | 2.4% | estimated ± 0.2 pp, medium confidence |
| SimpleQA | 33.9% | estimated ± 4.3 pp, low confidence |
| LiveCodeBench | 75.8% | estimated ± 14.6 pp, low confidence |
| OpenHarmony Bench v1.0 | 51.3% | estimated ± 2.4 pp, high confidence |
| MRCRv2 | 56.1% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 60.7% | estimated ± 2.6 pp, low confidence |
| BioBasicsBench | 33.9% | estimated ± 2.8 pp, low confidence |