Other · model
Atria Dawn Preview benchmark scores
As of 2026-10-07, Atria Dawn Preview (Other) has measured scores on 11 benchmarks and estimated scores on 46 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-SciCode | 50.1% | estimated ± 3.8 pp, high confidence |
| GDPval-AA | 24.8% | estimated ± 3.7 pp, low confidence |
| LiveCodeBench v6 | 89.4% | estimated ± 2.1 pp, high confidence |
| SciCode | 51.2% | estimated ± 4.8 pp, high confidence |
| Terminal-Bench 2.1 | 78.3% | measured |
| BrowseComp | 92.5% | measured |
| HLE w/ tools | 55.6% | estimated ± 2.4 pp, medium confidence |
| VITA-Bench | 46.6% | estimated ± 9.9 pp, low confidence |
| τ²-bench results | 94.8% | estimated ± 14.1 pp, low confidence |
| AA Coding Index | 64.8% | estimated ± 7.5 pp, medium confidence |
| APEX-Agents-AA | 38.3% | estimated ± 3.6 pp, medium confidence |
| DeepSearchQA | 96.0% | measured |
| SWE-bench Verified | 82.2% | estimated ± 2.5 pp, high confidence |
| AutomationBench | 53.8% | measured |
| BFCL v4 | 77.0% | measured |
| CyberGym | 86.5% | measured |
| JobBench | 50.3% | measured |
| SkillsBench | 66.4% | measured |
| SWE-bench Pro | 59.6% | measured |
| τ³-bench results | 41.2% | measured |
| WideResearch | 81.9% | measured |
| AA Agentic Index | 52.5% | estimated ± 5.8 pp, low confidence |
| Gert Labs | 70.3% | estimated ± 6.0 pp, low confidence |
| AA-AnalystAgent | 47.4% | estimated ± 12.5 pp, low confidence |
| AA EnterpriseOps-Gym | 30.0% | estimated ± 5.1 pp, low confidence |
| AA Harvey LAB | 93.5% | estimated ± 9.8 pp, low confidence |
| ApprenticeBench | 29.5% | estimated ± 4.0 pp, low confidence |
| CursorBench 3.1 | 54.4% | estimated ± 5.6 pp, low confidence |
| CursorBench 3.2 | 57.6% | estimated ± 3.6 pp, high confidence |
| Terminal-Bench 3.0 | 12.2% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 39.9% | estimated ± 5.5 pp, medium confidence |
| FrontierSWE v2 | 14.4% | estimated ± 9.0 pp, medium confidence |
| OSWorld-Verified | 80.4% | estimated ± 4.7 pp, high confidence |
| Vals LiveCodeBench | 84.7% | estimated ± 4.7 pp, medium confidence |
| Vals SWE-bench | 81.4% | estimated ± 7.5 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 66.4% | estimated ± 7.4 pp, medium confidence |
| AA AutomationBench | 53.6% | estimated ± 5.0 pp, medium confidence |
| GDP.pdf | 17.8% | estimated ± 5.2 pp, low confidence |
| AA Tau3 Banking | 41.4% | estimated ± 10.2 pp, low confidence |
| AA Terminal-Bench 2.1 | 84.3% | estimated ± 3.5 pp, high confidence |
| AA Terminal-Bench 4.0 | 16.5% | estimated ± 8.9 pp, medium confidence |
| CursorBench 4.0 | 35.2% | estimated ± 3.6 pp, medium confidence |
| OSWorld 2.0 | 68.6% | estimated ± 13.8 pp, low confidence |
| PostTrainBench v1.1 | 25.4% | estimated ± 4.7 pp, high confidence |
| Toolathlon-Verified | 73.2% | estimated ± 1.3 pp, low confidence |
| ExploitGym | 39.9% | estimated ± 6.1 pp, low confidence |
| Claw-Eval | 64.7% | estimated ± 2.3 pp, low confidence |
| DeepPlanning | 13.0% | estimated ± 8.3 pp, low confidence |
| MCP Atlas | 78.1% | estimated ± 8.2 pp, medium confidence |
| MCP-Tasks | 7.3% | estimated ± 3.6 pp, low confidence |
| NL2Repo | 47.0% | estimated ± 6.4 pp, medium confidence |
| Toolathlon | 57.3% | estimated ± 3.5 pp, medium confidence |
| LiveCodeBench Pro | 83.4% | estimated ± 6.0 pp, low confidence |
| ResearchClawBench | 20.0% | estimated ± 2.2 pp, low confidence |
| FrontierCode 1.1 Extended | 55.9% | estimated ± 3.0 pp, low confidence |
| Agents' Last Exam | 30.3% | estimated ± 2.1 pp, high confidence |
| OpenHarmony Bench | 53.4% | estimated ± 4.9 pp, low confidence |