Other · model
Trinity-Large-Thinking benchmark scores
As of 2026-10-07, Trinity-Large-Thinking (Other) has measured scores on 15 benchmarks and estimated scores on 77 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 75.2% | measured |
| AA-HLE | 15.8% | measured |
| AA-SciCode | 40.6% | measured |
| Artificial Analysis Intelligence Index | 10.8% | measured |
| CritPt | 0.9% | measured |
| GDPval-AA | 0.0% | measured |
| GPQA Diamond | 76.3% | measured |
| HLE | 15.6% | estimated ± 9.2 pp, medium confidence |
| IFBench | 59.5% | estimated ± 6.9 pp, medium confidence |
| AA-LCR | 38.0% | measured |
| LiveCodeBench v6 | 73.7% | estimated ± 3.1 pp, high confidence |
| AA-Omniscience Accuracy | 22.5% | measured |
| SciCode | 40.6% | estimated ± 3.2 pp, high confidence |
| BrowseComp | 58.6% | estimated ± 5.7 pp, medium confidence |
| HLE w/ tools | 31.6% | estimated ± 6.1 pp, low confidence |
| IFEval | 92.3% | estimated ± 1.3 pp, high confidence |
| LongBench v2 | 0.0% | estimated ± 5.9 pp, low confidence |
| τ²-bench results | 90.1% | measured |
| AA Coding Index | 25.8% | measured |
| APEX-Agents | 0.0% | estimated ± 10.0 pp, low confidence |
| APEX-Agents-AA | 4.7% | estimated ± 9.1 pp, medium confidence |
| BioMysteryBench (human-difficult) | 29.3% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 23.2% | estimated ± 4.5 pp, medium confidence |
| SWE-bench Verified | 47.5% | estimated ± 5.5 pp, medium confidence |
| AutomationBench | 28.4% | estimated ± 9.7 pp, low confidence |
| BFCL v4 | 53.8% | estimated ± 2.6 pp, high confidence |
| CyberGym | 46.4% | estimated ± 5.3 pp, low confidence |
| JobBench | 0.0% | estimated ± 8.6 pp, low confidence |
| SWE-bench Pro | 32.9% | estimated ± 6.0 pp, medium confidence |
| τ³-bench results | 100.0% | estimated ± 8.9 pp, low confidence |
| WideResearch | 34.6% | estimated ± 5.9 pp, low confidence |
| AA Agentic Index | 1.2% | measured |
| MMLU-Pro | 85.4% | estimated ± 3.5 pp, high confidence |
| GPQA | 76.3% | estimated ± 0.4 pp, high confidence |
| AA-IFBench | 56.3% | measured |
| Gert Labs | 32.6% | measured |
| AA-AnalystAgent | 0.0% | estimated ± 12.0 pp, low confidence |
| AA EnterpriseOps-Gym | 38.0% | estimated ± 3.6 pp, medium confidence |
| AA Harvey LAB | 79.4% | estimated ± 1.2 pp, low confidence |
| ApprenticeBench | 0.0% | estimated ± 3.1 pp, low confidence |
| ARC-AGI-1 | 62.0% | estimated ± 2.7 pp, medium confidence |
| ARC-AGI-2 | 25.1% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 20.8% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 15.3% | estimated ± 4.4 pp, medium confidence |
| FrontierCode 1.1 Main | 8.3% | estimated ± 3.8 pp, medium confidence |
| FrontierSWE v2 | 0.0% | estimated ± 14.6 pp, low confidence |
| OSWorld-Verified | 52.5% | estimated ± 5.9 pp, medium confidence |
| Vals GPQA Diamond | 75.2% | estimated ± 2.0 pp, medium confidence |
| Vals MMLU-Pro | 78.6% | estimated ± 1.6 pp, medium confidence |
| Vals SWE-bench | 52.4% | estimated ± 5.4 pp, low confidence |
| AA AutomationBench | 3.7% | estimated ± 7.0 pp, low confidence |
| GDP.pdf | 9.4% | estimated ± 5.4 pp, low confidence |
| AA ITBench | 48.8% | estimated ± 3.6 pp, medium confidence |
| AA Tau3 Banking | 22.0% | estimated ± 5.8 pp, low confidence |
| CursorBench 4.0 | 6.0% | estimated ± 1.6 pp, medium confidence |
| CWE-bench v1 | 0.0% | estimated ± 6.9 pp, low confidence |
| DeepSWE | 0.3% | estimated ± 6.4 pp, low confidence |
| HLE w/o tools | 7.6% | estimated ± 4.4 pp, high confidence |
| OSWorld 2.0 | 0.0% | estimated ± 4.5 pp, low confidence |
| PostTrainBench v1.1 | 8.4% | estimated ± 6.1 pp, low confidence |
| Toolathlon-Verified | 4.6% | estimated ± 2.3 pp, low confidence |
| Vibe Code Bench | 7.7% | estimated ± 10.3 pp, low confidence |
| ExploitGym | 0.0% | estimated ± 12.2 pp, low confidence |
| C-Eval | 84.5% | estimated ± 1.0 pp, low confidence |
| Claw-Eval | 51.0% | estimated ± 6.8 pp, low confidence |
| MCP Atlas | 64.6% | estimated ± 7.8 pp, low confidence |
| MCP-Tasks | 69.5% | estimated ± 8.2 pp, low confidence |
| MMLU-Redux | 94.0% | estimated ± 1.1 pp, medium confidence |
| NL2Repo | 17.2% | estimated ± 5.1 pp, low confidence |
| QwenClawBench | 55.9% | estimated ± 6.0 pp, low confidence |
| SuperGPQA | 67.3% | estimated ± 7.5 pp, medium confidence |
| Toolathlon | 26.9% | estimated ± 6.3 pp, low confidence |
| HealthBench Hard | 0.2% | estimated ± 7.7 pp, low confidence |
| MedXpertQA (Text) | 28.5% | estimated ± 4.5 pp, low confidence |
| MMLU-Pro (Arcee) | 83.4% | measured |
| React Native Evals | 70.5% | estimated ± 3.5 pp, high confidence |
| ResearchClawBench | 2.4% | estimated ± 2.0 pp, medium confidence |
| SWE-Rebench | 0.0% | estimated ± 8.9 pp, low confidence |
| ARC-AGI-3 | 1.7% | estimated ± 3.4 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| DRACO | 61.5% | estimated ± 3.0 pp, low confidence |
| FrontierCode 1.1 Extended | 25.4% | estimated ± 3.4 pp, low confidence |
| HealthBench (raw) | 22.8% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 25.3% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 35.3% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 56.7% | estimated ± 1.8 pp, low confidence |
| LiveCodeBench | 43.3% | estimated ± 8.9 pp, low confidence |
| OpenHarmony Bench | 51.0% | estimated ± 2.4 pp, medium confidence |
| MMMLU | 81.6% | estimated ± 1.1 pp, low confidence |
| MMLU | 87.7% | estimated ± 1.1 pp, medium confidence |