Other · model
dots3-note Preview benchmark scores
As of 2026-10-07, dots3-note Preview (Other) has measured scores on 27 benchmarks and estimated scores on 82 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 93.2% | estimated ± 2.7 pp, high confidence |
| AA-HLE | 47.3% | estimated ± 6.3 pp, medium confidence |
| AA-SciCode | 50.8% | estimated ± 3.0 pp, high confidence |
| Artificial Analysis Intelligence Index | 45.8% | estimated ± 7.0 pp, medium confidence |
| CritPt | 23.0% | estimated ± 5.7 pp, medium confidence |
| GDPval-AA | 24.0% | estimated ± 3.7 pp, low confidence |
| GPQA Diamond | 93.7% | estimated ± 1.5 pp, high confidence |
| HLE | 52.6% | measured |
| IFBench | 80.4% | measured |
| LiveCodeBench v6 | 91.5% | measured |
| AA-Omniscience Accuracy | 55.2% | estimated ± 6.2 pp, medium confidence |
| SciCode | 47.8% | estimated ± 3.8 pp, high confidence |
| Terminal-Bench 2.1 | 75.1% | measured |
| BrowseComp | 83.3% | measured |
| HLE w/ tools | 52.6% | measured |
| IFEval | 93.9% | measured |
| VITA-Bench | 45.3% | estimated ± 9.9 pp, low confidence |
| AA Coding Index | 68.1% | estimated ± 4.6 pp, high confidence |
| AA-MMMU-Pro | 79.7% | estimated ± 3.0 pp, medium confidence |
| APEX-Agents | 30.8% | measured |
| APEX-Agents-AA | 30.8% | estimated ± 4.6 pp, high confidence |
| DeepSearchQA | 92.1% | measured |
| SWE-bench Verified | 78.4% | measured |
| AutomationBench | 31.8% | estimated ± 10.3 pp, low confidence |
| BFCL v4 | 93.7% | estimated ± 8.6 pp, low confidence |
| CyberGym | 77.8% | estimated ± 2.4 pp, medium confidence |
| JobBench | 19.9% | estimated ± 3.4 pp, low confidence |
| SkillsBench | 52.8% | measured |
| SWE-bench Pro | 61.0% | measured |
| τ³-bench results | 67.9% | estimated ± 11.4 pp, low confidence |
| WideResearch | 78.9% | measured |
| AA Agentic Index | 26.5% | estimated ± 3.3 pp, medium confidence |
| MMLU-Pro | 86.3% | estimated ± 3.6 pp, high confidence |
| GPQA | 93.6% | estimated ± 1.6 pp, high confidence |
| AA-IFBench | 72.8% | estimated ± 8.2 pp, medium confidence |
| Gert Labs | 54.5% | estimated ± 6.1 pp, low confidence |
| AA-AnalystAgent | 41.9% | estimated ± 2.5 pp, medium confidence |
| AA EnterpriseOps-Gym | 42.1% | estimated ± 6.9 pp, low confidence |
| AA Harvey LAB | 88.7% | estimated ± 1.7 pp, medium confidence |
| ApprenticeBench | 23.1% | estimated ± 10.1 pp, low confidence |
| ARC-AGI-1 | 95.0% | estimated ± 1.9 pp, high confidence |
| ARC-AGI-2 | 81.4% | measured |
| CursorBench 3.1 | 55.3% | estimated ± 5.6 pp, low confidence |
| CursorBench 3.2 | 59.4% | estimated ± 3.6 pp, high confidence |
| Terminal-Bench 3.0 | 10.3% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 19.9% | estimated ± 2.7 pp, low confidence |
| FrontierSWE v2 | 16.9% | estimated ± 9.0 pp, medium confidence |
| OSWorld-Verified | 76.6% | estimated ± 5.4 pp, medium confidence |
| Vals GPQA Diamond | 93.4% | estimated ± 2.2 pp, high confidence |
| Vals LiveCodeBench | 85.2% | estimated ± 4.7 pp, medium confidence |
| Vals MMLU-Pro | 89.9% | estimated ± 2.0 pp, high confidence |
| Vals SWE-bench | 83.8% | estimated ± 5.4 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 64.0% | estimated ± 7.4 pp, medium confidence |
| AA AutomationBench | 20.2% | estimated ± 5.7 pp, low confidence |
| GDP.pdf | 9.5% | estimated ± 6.6 pp, low confidence |
| AA ITBench | 53.8% | estimated ± 3.4 pp, low confidence |
| AA Tau3 Banking | 30.9% | estimated ± 10.2 pp, low confidence |
| AA Terminal-Bench 2.1 | 82.9% | estimated ± 3.5 pp, high confidence |
| AA Terminal-Bench 4.0 | 12.8% | estimated ± 8.9 pp, medium confidence |
| CursorBench 4.0 | 36.2% | estimated ± 3.6 pp, medium confidence |
| DeepSWE | 49.3% | estimated ± 9.6 pp, medium confidence |
| HLE w/o tools | 42.9% | estimated ± 5.3 pp, medium confidence |
| OSWorld 2.0 | 19.4% | estimated ± 5.5 pp, low confidence |
| PostTrainBench v1.1 | 26.3% | estimated ± 4.7 pp, high confidence |
| SWE Multilingual | 75.7% | measured |
| Toolathlon-Verified | 55.6% | measured |
| Vibe Code Bench | 28.1% | estimated ± 8.1 pp, medium confidence |
| CharXiv | 89.5% | estimated ± 2.5 pp, high confidence |
| CharXiv w/o tools | 83.1% | measured |
| ExploitGym | 10.1% | estimated ± 6.1 pp, low confidence |
| C-Eval | 93.3% | estimated ± 0.8 pp, low confidence |
| Claw-Eval | 73.4% | measured |
| HMMT Feb 2026 | 97.3% | estimated ± 9.7 pp, low confidence |
| MathVision | 87.7% | measured |
| MCP Atlas | 77.0% | estimated ± 0.7 pp, medium confidence |
| MCP-Tasks | 79.1% | estimated ± 6.0 pp, low confidence |
| MMLU-ProX | 85.0% | estimated ± 1.7 pp, medium confidence |
| MMLU-Redux | 96.8% | estimated ± 2.1 pp, low confidence |
| MMMU-Pro | 79.1% | measured |
| NL2Repo | 49.8% | measured |
| NOVA-63 | 57.4% | estimated ± 1.6 pp, low confidence |
| ScreenSpot Pro | 84.6% | estimated ± 2.5 pp, medium confidence |
| SuperGPQA | 83.8% | estimated ± 9.1 pp, medium confidence |
| Toolathlon | 53.9% | estimated ± 3.5 pp, high confidence |
| V* | 93.6% | estimated ± 5.1 pp, medium confidence |
| VideoMMMU | 86.8% | measured |
| ERQA | 65.6% | estimated ± 2.4 pp, low confidence |
| LiveCodeBench Pro | 84.5% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (MM) | 72.6% | estimated ± 2.4 pp, high confidence |
| ResearchClawBench | 19.7% | estimated ± 1.3 pp, high confidence |
| SWE-Rebench | 61.6% | estimated ± 3.6 pp, medium confidence |
| ARC-AGI-3 | 0.3% | estimated ± 11.5 pp, low confidence |
| FrontierCode 1.1 Extended | 56.3% | estimated ± 3.0 pp, low confidence |
| HealthBench Professional | 55.8% | estimated ± 4.6 pp, high confidence |
| HLE-Verified | 35.9% | estimated ± 0.7 pp, low confidence |
| LABBench2 | 80.7% | estimated ± 2.5 pp, low confidence |
| MMMU | 85.1% | estimated ± 1.1 pp, low confidence |
| LiveCodeBench | 85.5% | estimated ± 10.2 pp, low confidence |
| OpenHarmony Bench | 55.2% | estimated ± 2.7 pp, high confidence |
| IMOAnswerBench | 90.9% | measured |
| BabyVision | 50.0% | measured |
| MMVU | 79.9% | measured |
| SimpleVQA | 72.5% | measured |
| ZeroBench | 19.0% | measured |
| MMMU-Pro w/ Python | 80.4% | estimated ± 0.6 pp, high confidence |
| MathVision w/ Python | 93.8% | estimated ± 0.5 pp, low confidence |
| RealWorldQA | 26.0% | estimated ± 0.8 pp, low confidence |
| Video-MME (with subtitle) | 88.8% | estimated ± 1.2 pp, medium confidence |
| OmniDocBench 1.5 | 91.7% | estimated ± 5.9 pp, low confidence |