Other · model
LongCat-2.5 benchmark scores
As of 2026-11-19, LongCat-2.5 (Other) has measured scores on 16 benchmarks and estimated scores on 79 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-SciCode | 53.3% | estimated ± 3.1 pp, high confidence |
| GDPval-AA | 57.6% | estimated ± 6.2 pp, medium confidence |
| LiveCodeBench v6 | 95.1% | estimated ± 1.9 pp, medium confidence |
| SciCode | 57.0% | estimated ± 7.6 pp, low confidence |
| Terminal-Bench 2.1 | 88.4% | measured |
| BrowseComp | 91.9% | measured |
| HLE w/ tools | 63.1% | measured |
| VITA-Bench | 47.4% | estimated ± 6.7 pp, low confidence |
| τ²-bench results | 98.6% | estimated ± 3.1 pp, medium confidence |
| AA Coding Index | 74.5% | estimated ± 2.5 pp, high confidence |
| AA-MMMU-Pro | 81.0% | estimated ± 4.9 pp, medium confidence |
| APEX-Agents | 58.0% | estimated ± 7.4 pp, low confidence |
| APEX-Agents-AA | 42.6% | estimated ± 3.6 pp, low confidence |
| DeepSearchQA | 93.5% | estimated ± 7.0 pp, low confidence |
| SWE-bench Verified | 81.9% | estimated ± 2.3 pp, high confidence |
| AutomationBench | 51.8% | measured |
| BFCL v4 | 76.8% | estimated ± 4.7 pp, low confidence |
| CyberGym | 87.5% | estimated ± 4.6 pp, medium confidence |
| JobBench | 65.4% | measured |
| SkillsBench | 63.3% | measured |
| SWE-bench Pro | 62.4% | estimated ± 3.5 pp, high confidence |
| WideResearch | 84.6% | estimated ± 1.2 pp, low confidence |
| AA Agentic Index | 52.7% | estimated ± 8.2 pp, medium confidence |
| Vals LiveCodeBench | 77.4% | estimated ± 6.1 pp, low confidence |
| MMMU | 90.7% | estimated ± 3.7 pp, low confidence |
| Gert Labs | 79.9% | estimated ± 7.1 pp, low confidence |
| AA EnterpriseOps-Gym | 46.8% | estimated ± 1.2 pp, medium confidence |
| AA Harvey LAB v1.0 | 91.8% | estimated ± 1.7 pp, medium confidence |
| AA Tau3 Banking | 50.1% | estimated ± 3.3 pp, low confidence |
| AA Terminal-Bench 2.1 | 86.2% | estimated ± 2.6 pp, high confidence |
| ApprenticeBench | 19.5% | estimated ± 6.0 pp, low confidence |
| CursorBench 3.2 | 26.6% | estimated ± 3.6 pp, low confidence |
| Terminal-Bench 3.0 | 23.7% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 46.9% | estimated ± 3.5 pp, low confidence |
| MazeBench | 0.1% | estimated ± 5.1 pp, medium confidence |
| OSWorld-Verified | 73.9% | estimated ± 3.8 pp, low confidence |
| ParseBench-1 | 69.0% | estimated ± 8.6 pp, low confidence |
| Terminal-Bench 4.1 | 32.9% | estimated ± 5.0 pp, medium confidence |
| Vals SWE-bench | 94.1% | estimated ± 5.2 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 74.0% | estimated ± 7.3 pp, medium confidence |
| CWE-Bench-AA | 60.6% | estimated ± 5.2 pp, medium confidence |
| AA Cyber Index | 46.3% | estimated ± 9.4 pp, medium confidence |
| DeepsecBench-AA | 27.0% | estimated ± 9.0 pp, low confidence |
| AA ITBench | 50.8% | estimated ± 4.1 pp, high confidence |
| Bug Hunt Bench | 25.9% | estimated ± 7.2 pp, low confidence |
| CursorBench 4.0 | 46.0% | estimated ± 4.7 pp, high confidence |
| DeepSWE | 64.6% | measured |
| DRACO | 87.5% | estimated ± 2.9 pp, low confidence |
| OSWorld 2.1 | 75.4% | estimated ± 7.2 pp, low confidence |
| PostTrainBench v1.1 | 32.7% | estimated ± 4.5 pp, high confidence |
| ProgramBench | 25.5% | measured |
| Terminal-Bench 4.0 | 38.5% | measured |
| Terminal-Bench-Science 0.1 | 15.2% | estimated ± 14.9 pp, low confidence |
| Toolathlon-Verified | 76.6% | estimated ± 5.7 pp, medium confidence |
| VulcanBench Frontier v4 | 88.5% | estimated ± 1.2 pp, low confidence |
| AA AutomationBench | 68.0% | estimated ± 7.9 pp, low confidence |
| GDP.pdf | 21.9% | estimated ± 4.1 pp, medium confidence |
| AA Terminal-Bench 4.0 | 36.0% | estimated ± 6.3 pp, medium confidence |
| CWE-bench | 62.3% | estimated ± 11.0 pp, low confidence |
| MKA | 40.8% | estimated ± 6.6 pp, medium confidence |
| Hermes Bench | 70.3% | estimated ± 1.5 pp, medium confidence |
| Hermes Index | 37.2% | estimated ± 7.0 pp, low confidence |
| CharXiv | 90.2% | measured |
| CharXiv w/o tools | 85.1% | estimated ± 1.9 pp, low confidence |
| ExploitGym | 32.3% | estimated ± 9.2 pp, low confidence |
| AI2D_TEST | 93.5% | estimated ± 0.9 pp, low confidence |
| Claw-Eval | 78.3% | measured |
| CountBench | 98.5% | estimated ± 3.7 pp, low confidence |
| DeepPlanning | 51.5% | estimated ± 13.1 pp, low confidence |
| DynaMath | 88.0% | estimated ± 0.8 pp, low confidence |
| ERQA | 71.2% | estimated ± 5.6 pp, medium confidence |
| MathVision | 92.5% | estimated ± 0.7 pp, medium confidence |
| MCP Atlas | 83.1% | measured |
| MLVU (M-Avg) | 89.0% | estimated ± 1.5 pp, high confidence |
| MMMU-Pro | 81.7% | estimated ± 2.9 pp, high confidence |
| NL2Repo | 60.5% | measured |
| QwenClawBench | 68.5% | estimated ± 2.6 pp, medium confidence |
| RealWorldQA | 87.4% | estimated ± 1.5 pp, high confidence |
| ScreenSpot Pro | 86.5% | estimated ± 6.8 pp, medium confidence |
| Toolathlon | 63.1% | estimated ± 4.2 pp, high confidence |
| Video-MME (with subtitle) | 90.8% | estimated ± 2.9 pp, high confidence |
| VideoMMMU | 87.3% | estimated ± 1.5 pp, medium confidence |
| We-Math | 84.6% | estimated ± 7.9 pp, low confidence |
| MedXpertQA (MM) | 79.1% | estimated ± 6.4 pp, low confidence |
| ResearchClawBench | 22.8% | estimated ± 1.3 pp, medium confidence |
| ScarfBench | 64.4% | estimated ± 3.8 pp, medium confidence |
| Agents' Last Exam | 38.5% | measured |
| OpenHarmony Bench v1.0 | 59.3% | estimated ± 2.7 pp, high confidence |
| BabyVision | 70.1% | estimated ± 10.4 pp, low confidence |
| MMVU | 80.7% | estimated ± 3.6 pp, medium confidence |
| SWE-Marathon | 42.6% | estimated ± 12.9 pp, low confidence |
| LifeVal | 80.6% | estimated ± 1.6 pp, medium confidence |
| MathVision w/ Python | 96.5% | measured |
| PinchBench | 90.8% | estimated ± 3.6 pp, low confidence |
| SWE-Atlas Codebase QnA | 58.3% | measured |