Other · model
Ornith-1.5-397B benchmark scores
As of 2026-10-07, Ornith-1.5-397B (Other) has measured scores on 17 benchmarks and estimated scores on 71 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 91.2% | estimated ± 2.7 pp, high confidence |
| AA-HLE | 43.1% | estimated ± 4.0 pp, high confidence |
| AA-SciCode | 52.8% | estimated ± 3.0 pp, high confidence |
| Artificial Analysis Intelligence Index | 38.3% | estimated ± 5.1 pp, medium confidence |
| CritPt | 18.8% | estimated ± 4.1 pp, high confidence |
| GDPval-AA | 24.6% | estimated ± 3.7 pp, low confidence |
| GPQA Diamond | 92.8% | measured |
| HLE | 44.6% | measured |
| LiveCodeBench v6 | 90.7% | estimated ± 2.1 pp, high confidence |
| AA-Omniscience Accuracy | 45.4% | estimated ± 8.1 pp, medium confidence |
| SciCode | 51.2% | estimated ± 3.8 pp, medium confidence |
| Terminal-Bench 2.1 | 86.1% | measured |
| BrowseComp | 86.6% | measured |
| HLE w/ tools | 56.1% | measured |
| VITA-Bench | 48.2% | estimated ± 9.9 pp, low confidence |
| AA Coding Index | 71.8% | estimated ± 2.5 pp, high confidence |
| APEX-Agents | 33.9% | estimated ± 0.6 pp, medium confidence |
| APEX-Agents-AA | 35.6% | estimated ± 4.6 pp, high confidence |
| DeepSearchQA | 89.6% | estimated ± 8.1 pp, low confidence |
| SWE-bench Verified | 86.0% | measured |
| AutomationBench | 34.8% | estimated ± 10.3 pp, low confidence |
| BFCL v4 | 100.0% | estimated ± 8.6 pp, low confidence |
| CyberGym | 79.2% | estimated ± 2.4 pp, medium confidence |
| JobBench | 52.3% | estimated ± 3.4 pp, low confidence |
| SkillsBench | 61.3% | estimated ± 5.6 pp, low confidence |
| SWE-bench Pro | 65.1% | measured |
| τ³-bench results | 69.6% | estimated ± 1.8 pp, low confidence |
| WideResearch | 80.8% | measured |
| AA Agentic Index | 46.8% | estimated ± 3.3 pp, medium confidence |
| MMLU-Pro | 85.7% | estimated ± 2.5 pp, low confidence |
| GPQA | 92.8% | measured |
| Gert Labs | 55.5% | estimated ± 6.1 pp, low confidence |
| AA-AnalystAgent | 49.6% | estimated ± 2.5 pp, medium confidence |
| AA EnterpriseOps-Gym | 43.2% | estimated ± 6.9 pp, low confidence |
| AA Harvey LAB | 89.8% | estimated ± 1.7 pp, medium confidence |
| ARC-AGI-1 | 93.1% | estimated ± 2.7 pp, high confidence |
| ARC-AGI-2 | 70.1% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 57.9% | estimated ± 5.6 pp, low confidence |
| CursorBench 3.2 | 63.7% | estimated ± 3.6 pp, high confidence |
| Terminal-Bench 3.0 | 13.5% | measured |
| FrontierCode 1.1 Main | 43.1% | estimated ± 2.7 pp, medium confidence |
| FrontierSWE v2 | 24.2% | estimated ± 9.0 pp, medium confidence |
| OSWorld-Verified | 80.9% | estimated ± 5.4 pp, medium confidence |
| Vals GPQA Diamond | 92.1% | estimated ± 2.0 pp, high confidence |
| Vals LiveCodeBench | 86.5% | estimated ± 4.7 pp, medium confidence |
| Vals MMLU-Pro | 88.1% | estimated ± 1.2 pp, high confidence |
| Vals SWE-bench | 92.6% | estimated ± 5.4 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 75.0% | estimated ± 3.4 pp, high confidence |
| AA AutomationBench | 37.9% | estimated ± 5.7 pp, low confidence |
| GDP.pdf | 10.6% | estimated ± 6.6 pp, low confidence |
| AA ITBench | 50.8% | estimated ± 3.4 pp, medium confidence |
| AA Tau3 Banking | 34.3% | estimated ± 10.2 pp, low confidence |
| AA Terminal-Bench 2.1 | 84.9% | estimated ± 3.5 pp, high confidence |
| AA Terminal-Bench 4.0 | 26.1% | estimated ± 8.9 pp, medium confidence |
| CursorBench 4.0 | 39.4% | estimated ± 3.6 pp, high confidence |
| DeepSWE | 56.0% | measured |
| HLE w/o tools | 44.6% | measured |
| OSWorld 2.0 | 19.4% | estimated ± 5.5 pp, low confidence |
| PostTrainBench v1.1 | 28.9% | estimated ± 4.7 pp, high confidence |
| SWE Multilingual | 79.6% | measured |
| Toolathlon-Verified | 71.2% | measured |
| Vibe Code Bench | 62.3% | estimated ± 8.1 pp, low confidence |
| ExploitGym | 20.8% | estimated ± 6.1 pp, low confidence |
| C-Eval | 93.3% | estimated ± 0.8 pp, low confidence |
| Claw-Eval | 81.4% | measured |
| DeepPlanning | 50.1% | estimated ± 13.1 pp, low confidence |
| MCP Atlas | 80.0% | measured |
| MCP-Tasks | 77.1% | estimated ± 0.6 pp, low confidence |
| MMLU-ProX | 86.5% | estimated ± 1.7 pp, low confidence |
| MMLU-Redux | 96.3% | estimated ± 2.1 pp, low confidence |
| NL2Repo | 59.5% | measured |
| NOVA-63 | 59.1% | estimated ± 1.6 pp, low confidence |
| QwenClawBench | 65.9% | estimated ± 2.6 pp, medium confidence |
| SuperGPQA | 80.5% | estimated ± 9.1 pp, medium confidence |
| Toolathlon | 55.4% | estimated ± 3.5 pp, high confidence |
| HealthBench Hard | 34.4% | estimated ± 5.1 pp, low confidence |
| LiveCodeBench Pro | 87.5% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (Text) | 63.2% | estimated ± 4.5 pp, medium confidence |
| MMLU-Pro (Arcee) | 87.8% | estimated ± 3.4 pp, low confidence |
| ResearchClawBench | 21.6% | estimated ± 1.3 pp, medium confidence |
| SWE-Rebench | 61.8% | estimated ± 3.6 pp, low confidence |
| ARC-AGI-3 | 0.2% | estimated ± 2.1 pp, high confidence |
| FrontierCode 1.1 Extended | 57.6% | estimated ± 3.0 pp, medium confidence |
| HealthBench Professional | 55.6% | estimated ± 4.8 pp, medium confidence |
| LiveCodeBench | 90.1% | estimated ± 10.2 pp, low confidence |
| OpenHarmony Bench | 59.3% | estimated ± 2.7 pp, high confidence |
| MMMLU | 90.7% | estimated ± 1.1 pp, low confidence |
| MMLU | 90.5% | estimated ± 3.6 pp, low confidence |