Other · model
Ornith-1.0-397B benchmark scores
As of 2026-11-22, Ornith-1.0-397B (Other) has measured scores on 6 benchmarks and estimated scores on 37 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-SciCode | 49.5% | estimated ± 3.1 pp, high confidence |
| LiveCodeBench v6 | 91.6% | estimated ± 1.7 pp, high confidence |
| SciCode | 48.7% | estimated ± 3.6 pp, medium confidence |
| Terminal-Bench 2.1 | 77.5% | measured |
| VITA-Bench | 54.9% | estimated ± 10.7 pp, low confidence |
| AA Coding Index | 66.9% | estimated ± 4.3 pp, high confidence |
| SWE-bench Verified | 82.4% | measured |
| JobBench | 57.8% | estimated ± 9.3 pp, low confidence |
| SWE-bench Pro | 62.2% | measured |
| Vals LiveCodeBench | 85.5% | estimated ± 4.7 pp, medium confidence |
| AA Terminal-Bench 2.1 | 81.7% | estimated ± 2.6 pp, high confidence |
| CursorBench 3.1 | 56.1% | estimated ± 5.6 pp, low confidence |
| CursorBench 3.2 | 60.8% | estimated ± 3.6 pp, high confidence |
| Terminal-Bench 3.0 | 11.7% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 31.7% | estimated ± 4.2 pp, medium confidence |
| FrontierSWE v2 | 19.4% | estimated ± 8.3 pp, medium confidence |
| OSWorld-Verified | 73.8% | estimated ± 3.8 pp, low confidence |
| Terminal-Bench 4.1 | 14.7% | estimated ± 10.9 pp, low confidence |
| Vals SWE-bench | 81.9% | estimated ± 5.2 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 65.7% | estimated ± 7.3 pp, medium confidence |
| Bug Hunt Bench | 15.0% | estimated ± 7.2 pp, low confidence |
| CursorBench 4.0 | 37.2% | estimated ± 3.3 pp, medium confidence |
| DeepSWE | 47.4% | estimated ± 8.7 pp, medium confidence |
| FrontierCode 2.0 | 21.9% | estimated ± 6.7 pp, medium confidence |
| PostTrainBench v1.1 | 27.0% | estimated ± 4.4 pp, high confidence |
| SWE Multilingual | 78.9% | measured |
| VulcanBench Frontier v4 | 80.9% | estimated ± 8.3 pp, low confidence |
| AA Terminal-Bench 4.0 | 4.3% | estimated ± 11.0 pp, low confidence |
| Vibe Code Bench | 62.8% | estimated ± 8.4 pp, medium confidence |
| Claw-Eval | 77.1% | measured |
| INCLUDE | 86.1% | estimated ± 2.0 pp, medium confidence |
| MCP Atlas | 76.2% | estimated ± 13.5 pp, low confidence |
| MMLU-ProX | 86.3% | estimated ± 1.3 pp, medium confidence |
| NL2Repo | 48.2% | measured |
| PostTrainBench v1 | 27.5% | estimated ± 4.6 pp, high confidence |
| LiveCodeBench Pro | 85.4% | estimated ± 6.0 pp, low confidence |
| React Native Evals | 80.7% | estimated ± 2.7 pp, medium confidence |
| ResearchClawBench | 20.6% | estimated ± 1.3 pp, medium confidence |
| SWE-Rebench | 61.8% | estimated ± 3.6 pp, medium confidence |
| PostTrainBench | 24.9% | estimated ± 3.7 pp, high confidence |
| FrontierCode 1.1 Extended | 56.7% | estimated ± 3.0 pp, low confidence |
| LiveCodeBench | 80.7% | estimated ± 14.6 pp, low confidence |
| OpenHarmony Bench v1.0 | 55.4% | estimated ± 2.7 pp, high confidence |