Other · model
LongCat-Flash-Lite-Sparse benchmark scores
As of 2026-10-07, LongCat-Flash-Lite-Sparse (Other) has measured scores on 15 benchmarks and estimated scores on 74 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 83.0% | estimated ± 2.0 pp, low confidence |
| AA-HLE | 9.5% | estimated ± 4.0 pp, high confidence |
| AA-SciCode | 40.2% | estimated ± 3.8 pp, high confidence |
| AIME26 | 65.7% | measured |
| Artificial Analysis Intelligence Index | 10.0% | estimated ± 1.3 pp, medium confidence |
| CritPt | 0.1% | estimated ± 1.1 pp, low confidence |
| GDPval-AA | 19.8% | estimated ± 8.4 pp, medium confidence |
| GPQA Diamond | 69.5% | measured |
| HLE | 11.1% | estimated ± 2.5 pp, low confidence |
| LiveCodeBench v6 | 81.0% | estimated ± 2.1 pp, high confidence |
| AA-Omniscience Accuracy | 18.4% | estimated ± 1.8 pp, medium confidence |
| SciCode | 42.9% | estimated ± 3.8 pp, high confidence |
| BrowseComp | 48.6% | measured |
| HLE w/ tools | 33.2% | estimated ± 4.6 pp, high confidence |
| VITA-Bench | 21.7% | measured |
| AA Coding Index | 38.2% | estimated ± 5.1 pp, medium confidence |
| APEX-Agents | 6.3% | estimated ± 0.6 pp, low confidence |
| APEX-Agents-AA | 7.0% | estimated ± 4.6 pp, medium confidence |
| DeepSearchQA | 75.3% | estimated ± 8.1 pp, low confidence |
| SWE-bench Verified | 68.2% | measured |
| AutomationBench | 12.1% | estimated ± 10.3 pp, low confidence |
| CyberGym | 55.2% | estimated ± 4.6 pp, medium confidence |
| JobBench | 22.3% | estimated ± 6.8 pp, medium confidence |
| SWE-bench Pro | 40.6% | measured |
| τ³-bench results | 69.2% | estimated ± 1.8 pp, medium confidence |
| WideResearch | 60.2% | estimated ± 4.6 pp, medium confidence |
| AA Agentic Index | 12.2% | estimated ± 8.2 pp, medium confidence |
| MMLU-Pro | 79.2% | measured |
| FrontierMath v2 (Tiers 1-3) | 24.4% | estimated ± 8.4 pp, low confidence |
| GPQA | 69.5% | estimated ± 0.4 pp, high confidence |
| Gert Labs | 29.7% | estimated ± 7.4 pp, low confidence |
| AA-AnalystAgent | 5.0% | estimated ± 12.5 pp, low confidence |
| AA EnterpriseOps-Gym | 29.8% | estimated ± 6.9 pp, low confidence |
| AA Harvey LAB | 82.4% | estimated ± 9.8 pp, low confidence |
| ARC-AGI-1 | 45.5% | estimated ± 2.7 pp, medium confidence |
| ARC-AGI-2 | 18.6% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 40.6% | estimated ± 5.6 pp, low confidence |
| CursorBench 3.2 | 18.7% | estimated ± 3.6 pp, medium confidence |
| FrontierCode 1.1 Main | 2.4% | estimated ± 2.7 pp, low confidence |
| FrontierSWE v2 | 0.0% | estimated ± 9.0 pp, low confidence |
| OSWorld-Verified | 47.8% | estimated ± 5.4 pp, low confidence |
| Vals GPQA Diamond | 68.2% | estimated ± 2.0 pp, medium confidence |
| Vals LiveCodeBench | 57.8% | estimated ± 4.7 pp, low confidence |
| Vals MMLU-Pro | 74.2% | estimated ± 1.6 pp, medium confidence |
| Vals SWE-bench | 60.1% | estimated ± 6.8 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 29.2% | estimated ± 6.3 pp, low confidence |
| AA AutomationBench | 2.6% | estimated ± 5.7 pp, low confidence |
| GDP.pdf | 9.3% | estimated ± 6.6 pp, low confidence |
| AA ITBench | 21.1% | estimated ± 3.6 pp, low confidence |
| AA Tau3 Banking | 15.5% | estimated ± 10.2 pp, low confidence |
| CursorBench 4.0 | 20.6% | estimated ± 3.6 pp, medium confidence |
| HLE w/o tools | 6.0% | estimated ± 4.4 pp, medium confidence |
| OSWorld 2.0 | 17.7% | estimated ± 13.8 pp, low confidence |
| PostTrainBench v1.1 | 15.3% | estimated ± 4.7 pp, medium confidence |
| SWE Multilingual | 59.3% | measured |
| Toolathlon-Verified | 33.4% | estimated ± 7.7 pp, low confidence |
| Vibe Code Bench | 0.7% | estimated ± 8.1 pp, medium confidence |
| ExploitGym | 0.0% | estimated ± 6.1 pp, low confidence |
| C-Eval | 85.8% | measured |
| Claw-Eval | 60.0% | estimated ± 5.7 pp, medium confidence |
| DeepPlanning | 26.2% | estimated ± 9.1 pp, low confidence |
| HMMT Feb 2025 | 59.4% | estimated ± 1.8 pp, low confidence |
| HMMT Feb 2026 | 40.5% | measured |
| MCP Atlas | 45.6% | measured |
| MCP-Tasks | 73.5% | estimated ± 0.6 pp, medium confidence |
| MMAnswerBench | 44.0% | estimated ± 1.3 pp, medium confidence |
| MMLU-ProX | 78.6% | estimated ± 1.7 pp, low confidence |
| MMLU-Redux | 89.8% | estimated ± 0.7 pp, high confidence |
| NL2Repo | 24.8% | estimated ± 6.1 pp, low confidence |
| NOVA-63 | 49.7% | estimated ± 1.6 pp, low confidence |
| QwenClawBench | 52.0% | estimated ± 2.0 pp, low confidence |
| SuperGPQA | 56.1% | estimated ± 1.2 pp, low confidence |
| Terminal-Bench 2.0 | 33.7% | measured |
| Toolathlon | 13.2% | estimated ± 3.5 pp, medium confidence |
| LiveCodeBench Pro | 66.2% | estimated ± 6.0 pp, low confidence |
| MedXpertQA (Text) | 21.9% | estimated ± 4.5 pp, low confidence |
| MMLU-Pro (Arcee) | 78.7% | estimated ± 3.4 pp, medium confidence |
| ResearchClawBench | 15.8% | estimated ± 1.8 pp, medium confidence |
| SWE-Rebench | 57.0% | estimated ± 3.6 pp, low confidence |
| ARC-AGI-3 | 0.0% | estimated ± 3.8 pp, medium confidence |
| FrontierCode 1.1 Extended | 47.9% | estimated ± 3.0 pp, low confidence |
| HealthBench Professional | 15.8% | estimated ± 4.8 pp, low confidence |
| AIME 2025 | 57.3% | estimated ± 1.5 pp, medium confidence |
| LiveCodeBench | 78.8% | estimated ± 10.2 pp, low confidence |
| OpenHarmony Bench | 53.3% | estimated ± 4.9 pp, low confidence |
| IMOAnswerBench | 49.4% | measured |
| MMMLU | 73.6% | estimated ± 1.1 pp, low confidence |
| MMLU | 85.3% | measured |
| MATH-500 | 95.8% | measured |