Other · model
Ornith-1.5-9B benchmark scores
As of 2026-10-07, Ornith-1.5-9B (Other) has measured scores on 15 benchmarks and estimated scores on 73 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 83.9% | estimated ± 2.7 pp, high confidence |
| AA-HLE | 27.9% | estimated ± 4.0 pp, high confidence |
| AA-SciCode | 39.7% | estimated ± 3.0 pp, high confidence |
| Artificial Analysis Intelligence Index | 19.0% | estimated ± 5.1 pp, medium confidence |
| CritPt | 2.6% | estimated ± 4.1 pp, high confidence |
| GDPval-AA | 18.7% | estimated ± 3.7 pp, low confidence |
| GPQA Diamond | 86.4% | measured |
| HLE | 20.2% | measured |
| LiveCodeBench v6 | 83.8% | estimated ± 2.1 pp, high confidence |
| AA-Omniscience Accuracy | 26.1% | estimated ± 8.1 pp, medium confidence |
| SciCode | 44.1% | estimated ± 3.8 pp, high confidence |
| Terminal-Bench 2.1 | 46.2% | measured |
| BrowseComp | 56.4% | measured |
| HLE w/ tools | 30.5% | measured |
| VITA-Bench | 36.8% | estimated ± 9.9 pp, low confidence |
| AA Coding Index | 45.5% | estimated ± 4.6 pp, high confidence |
| APEX-Agents | 13.2% | estimated ± 0.6 pp, low confidence |
| APEX-Agents-AA | 8.8% | estimated ± 4.6 pp, medium confidence |
| DeepSearchQA | 76.3% | estimated ± 8.1 pp, low confidence |
| SWE-bench Verified | 70.6% | measured |
| AutomationBench | 15.2% | estimated ± 10.3 pp, low confidence |
| BFCL v4 | 74.2% | estimated ± 8.6 pp, low confidence |
| CyberGym | 76.3% | estimated ± 2.4 pp, low confidence |
| JobBench | 4.0% | estimated ± 3.4 pp, low confidence |
| SkillsBench | 17.1% | estimated ± 5.6 pp, low confidence |
| SWE-bench Pro | 47.5% | measured |
| τ³-bench results | 69.5% | estimated ± 1.8 pp, medium confidence |
| WideResearch | 59.5% | measured |
| AA Agentic Index | 7.7% | estimated ± 3.3 pp, low confidence |
| MMLU-Pro | 84.4% | estimated ± 2.5 pp, medium confidence |
| GPQA | 86.4% | measured |
| Gert Labs | 44.1% | estimated ± 6.1 pp, low confidence |
| AA-AnalystAgent | 4.5% | estimated ± 2.5 pp, low confidence |
| AA EnterpriseOps-Gym | 32.7% | estimated ± 6.9 pp, low confidence |
| AA Harvey LAB | 77.1% | estimated ± 1.7 pp, low confidence |
| ARC-AGI-1 | 83.2% | estimated ± 2.7 pp, medium confidence |
| ARC-AGI-2 | 43.5% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 45.9% | estimated ± 5.6 pp, low confidence |
| CursorBench 3.2 | 34.5% | estimated ± 3.6 pp, medium confidence |
| Terminal-Bench 3.0 | 3.1% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 4.2% | estimated ± 2.7 pp, low confidence |
| FrontierSWE v2 | 0.0% | estimated ± 9.0 pp, low confidence |
| OSWorld-Verified | 50.5% | estimated ± 5.4 pp, low confidence |
| Vals GPQA Diamond | 85.6% | estimated ± 2.0 pp, high confidence |
| Vals LiveCodeBench | 73.6% | estimated ± 4.7 pp, medium confidence |
| Vals MMLU-Pro | 83.7% | estimated ± 1.2 pp, high confidence |
| Vals SWE-bench | 63.9% | estimated ± 5.4 pp, low confidence |
| Terminal-Bench 2.1 (Vals AI) | 41.6% | estimated ± 7.4 pp, low confidence |
| AA AutomationBench | 2.6% | estimated ± 5.7 pp, low confidence |
| GDP.pdf | 9.3% | estimated ± 6.6 pp, low confidence |
| AA ITBench | 73.2% | estimated ± 3.4 pp, low confidence |
| AA Tau3 Banking | 16.5% | estimated ± 10.2 pp, low confidence |
| AA Terminal-Bench 2.1 | 52.1% | estimated ± 3.5 pp, medium confidence |
| AA Terminal-Bench 4.0 | 0.0% | estimated ± 8.9 pp, low confidence |
| CursorBench 4.0 | 25.9% | estimated ± 3.6 pp, medium confidence |
| DeepSWE | 27.8% | estimated ± 9.6 pp, low confidence |
| HLE w/o tools | 20.2% | measured |
| OSWorld 2.0 | 19.4% | estimated ± 5.5 pp, low confidence |
| PostTrainBench v1.1 | 18.6% | estimated ± 4.7 pp, medium confidence |
| SWE Multilingual | 54.4% | measured |
| Toolathlon-Verified | 41.2% | measured |
| Vibe Code Bench | 0.7% | estimated ± 8.1 pp, medium confidence |
| ExploitGym | 0.0% | estimated ± 6.1 pp, low confidence |
| C-Eval | 88.7% | estimated ± 0.8 pp, low confidence |
| Claw-Eval | 66.5% | measured |
| DeepPlanning | 36.9% | estimated ± 13.1 pp, low confidence |
| MCP Atlas | 54.2% | measured |
| MCP-Tasks | 75.8% | estimated ± 0.6 pp, low confidence |
| MMLU-ProX | 76.5% | estimated ± 1.7 pp, low confidence |
| MMLU-Redux | 92.5% | estimated ± 2.1 pp, medium confidence |
| NL2Repo | 32.4% | measured |
| NOVA-63 | 47.0% | estimated ± 1.6 pp, low confidence |
| QwenClawBench | 54.6% | estimated ± 2.6 pp, high confidence |
| SuperGPQA | 61.1% | estimated ± 9.1 pp, medium confidence |
| Toolathlon | 24.6% | estimated ± 3.5 pp, medium confidence |
| HealthBench Hard | 0.0% | estimated ± 5.1 pp, low confidence |
| LiveCodeBench Pro | 73.1% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (Text) | 44.6% | estimated ± 4.5 pp, low confidence |
| MMLU-Pro (Arcee) | 85.6% | estimated ± 3.4 pp, medium confidence |
| ResearchClawBench | 18.0% | estimated ± 1.3 pp, high confidence |
| SWE-Rebench | 57.0% | estimated ± 3.6 pp, medium confidence |
| ARC-AGI-3 | 0.0% | estimated ± 2.1 pp, medium confidence |
| FrontierCode 1.1 Extended | 51.2% | estimated ± 3.0 pp, low confidence |
| HealthBench Professional | 43.2% | estimated ± 4.8 pp, low confidence |
| LiveCodeBench | 80.4% | estimated ± 10.2 pp, low confidence |
| OpenHarmony Bench | 44.8% | estimated ± 2.7 pp, medium confidence |
| MMMLU | 88.4% | estimated ± 1.1 pp, medium confidence |
| MMLU | 90.3% | estimated ± 3.6 pp, low confidence |