Other · model
Ling 3.1 Flash benchmark scores
As of 2026-11-22, Ling 3.1 Flash (Other) has measured scores on 23 benchmarks and estimated scores on 113 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 96.2% | estimated ± 2.1 pp, low confidence |
| AA-HLE | 39.4% | measured |
| AA-SciCode | 54.1% | measured |
| Artificial Analysis Intelligence Index | 37.4% | estimated ± 7.2 pp, medium confidence |
| CritPt | 18.0% | measured |
| GDPval-AA | 55.9% | measured |
| GPQA Diamond | 96.3% | estimated ± 1.2 pp, medium confidence |
| HLE | 37.4% | measured |
| AA-LCR | 83.0% | measured |
| LiveCodeBench v6 | 92.8% | estimated ± 2.7 pp, high confidence |
| AA-Omniscience Accuracy | 31.8% | estimated ± 9.1 pp, medium confidence |
| SciCode | 53.8% | estimated ± 3.1 pp, high confidence |
| Terminal-Bench 2.1 | 81.2% | measured |
| BrowseComp | 91.7% | measured |
| HLE w/ tools | 63.6% | estimated ± 4.9 pp, medium confidence |
| LongBench v2 | 68.4% | estimated ± 5.5 pp, medium confidence |
| VITA-Bench | 47.3% | estimated ± 6.7 pp, low confidence |
| τ²-bench results | 93.6% | estimated ± 11.8 pp, low confidence |
| AA Coding Index | 73.0% | estimated ± 2.5 pp, high confidence |
| APEX-Agents | 65.7% | estimated ± 7.4 pp, low confidence |
| APEX-Agents-AA | 43.5% | estimated ± 4.4 pp, medium confidence |
| BioMysteryBench (human-difficult) | 47.6% | estimated ± 6.8 pp, low confidence |
| DeepSearchQA | 93.3% | estimated ± 6.8 pp, low confidence |
| SWE-bench Verified | 87.8% | estimated ± 3.6 pp, high confidence |
| AutomationBench | 52.5% | measured |
| BFCL v4 | 77.1% | estimated ± 2.7 pp, medium confidence |
| CyberGym | 87.9% | measured |
| JobBench | 59.1% | estimated ± 5.1 pp, low confidence |
| SkillsBench | 68.7% | measured |
| SWE-bench Pro | 68.7% | measured |
| τ³-bench results | 47.8% | measured |
| WideResearch | 83.3% | measured |
| AA Agentic Index | 52.0% | estimated ± 3.1 pp, high confidence |
| MMLU-Pro | 85.7% | estimated ± 14.4 pp, low confidence |
| GPQA | 96.3% | estimated ± 1.2 pp, medium confidence |
| Vals GPQA Diamond | 98.8% | estimated ± 1.2 pp, low confidence |
| Vals LiveCodeBench | 87.1% | estimated ± 4.7 pp, medium confidence |
| Vals MMLU-Pro | 85.7% | estimated ± 2.4 pp, medium confidence |
| MMMLU | 90.6% | estimated ± 0.7 pp, low confidence |
| Chess Puzzles | 41.5% | estimated ± 10.8 pp, low confidence |
| AA MMLU-Pro | 88.9% | estimated ± 1.3 pp, high confidence |
| Gert Labs | 58.6% | estimated ± 5.3 pp, low confidence |
| AA-AnalystAgent | 46.7% | estimated ± 3.7 pp, medium confidence |
| AA Harvey LAB v1.0 | 93.3% | estimated ± 9.8 pp, low confidence |
| AA Tau3 Banking | 100.0% | estimated ± 3.3 pp, low confidence |
| AA Terminal-Bench 2.1 | 81.7% | estimated ± 2.6 pp, high confidence |
| ApprenticeBench | 32.5% | estimated ± 4.0 pp, medium confidence |
| ARC-AGI-1 | 88.2% | estimated ± 7.8 pp, low confidence |
| ARC-AGI-2 | 65.2% | estimated ± 14.4 pp, low confidence |
| CursorBench 3.1 | 54.1% | estimated ± 3.4 pp, medium confidence |
| CursorBench 3.2 | 66.5% | estimated ± 3.6 pp, high confidence |
| EBR-bench | 33.6% | estimated ± 11.3 pp, low confidence |
| Terminal-Bench 3.0 | 14.4% | estimated ± 9.1 pp, low confidence |
| FrontierCode 1.1 Main | 44.1% | estimated ± 3.5 pp, low confidence |
| FrontierSWE v2 | 30.7% | estimated ± 8.3 pp, medium confidence |
| Furniture Assembly | 37.9% | estimated ± 12.4 pp, low confidence |
| MaxxBench | 51.6% | estimated ± 5.7 pp, medium confidence |
| MazeBench | 7.8% | estimated ± 5.5 pp, low confidence |
| Mystery Game Puzzles | 28.6% | estimated ± 13.3 pp, low confidence |
| OSWorld-Verified | 80.7% | estimated ± 4.7 pp, high confidence |
| Terminal-Bench 4.1 | 45.0% | estimated ± 4.6 pp, high confidence |
| Vals SWE-bench | 89.5% | estimated ± 7.2 pp, medium confidence |
| Terminal-Bench 2.1 (Vals AI) | 68.5% | estimated ± 7.3 pp, medium confidence |
| CWE-Bench-AA | 61.1% | estimated ± 6.0 pp, low confidence |
| AA Cyber Index | 46.3% | estimated ± 9.4 pp, medium confidence |
| DeepsecBench-AA | 26.4% | estimated ± 8.9 pp, low confidence |
| HealthBench Professional (length-adjusted, Artificial Analysis) | 56.5% | estimated ± 7.3 pp, low confidence |
| HealthBench Professional (raw, Artificial Analysis) | 64.2% | estimated ± 0.8 pp, low confidence |
| AA ITBench | 50.7% | estimated ± 4.1 pp, high confidence |
| Bug Hunt Bench | 22.1% | estimated ± 10.4 pp, low confidence |
| CursorBench 4.0 | 42.2% | estimated ± 3.3 pp, high confidence |
| CWE-bench v1 | 59.6% | estimated ± 6.4 pp, medium confidence |
| DeepSWE | 59.7% | measured |
| DRACO | 85.5% | measured |
| FrontierCode 2.0 | 25.1% | estimated ± 6.7 pp, medium confidence |
| FrontierPhysics | 2.2% | estimated ± 4.7 pp, high confidence |
| HLE w/o tools | 57.0% | estimated ± 4.9 pp, medium confidence |
| OSWorld 2.1 | 70.9% | estimated ± 6.0 pp, medium confidence |
| OSWorld 2.1 Offline | 72.7% | estimated ± 1.9 pp, medium confidence |
| PostTrainBench v1.1 | 31.4% | estimated ± 4.4 pp, high confidence |
| StealthMark | 42.4% | measured |
| SWE Multilingual | 88.5% | measured |
| Terminal-Bench 4.0 | 46.0% | measured |
| Terminal-Bench-Science 0.1 | 31.5% | estimated ± 14.2 pp, low confidence |
| Toolathlon-Verified | 75.4% | estimated ± 1.2 pp, medium confidence |
| VulcanBench Frontier v4 | 79.6% | estimated ± 5.0 pp, high confidence |
| GDP.pdf | 17.0% | estimated ± 4.6 pp, high confidence |
| AA Terminal-Bench 4.0 | 42.9% | estimated ± 6.3 pp, medium confidence |
| ARC-AGI-3 | 0.0% | estimated ± 8.3 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 2.7% | estimated ± 7.3 pp, medium confidence |
| cursorBench41 | 44.8% | estimated ± 3.7 pp, medium confidence |
| MKA | 41.9% | estimated ± 6.4 pp, low confidence |
| FACTS Multimodal | 41.6% | estimated ± 4.7 pp, high confidence |
| Hermes Bench | 72.1% | estimated ± 2.9 pp, high confidence |
| Hermes Index | 44.9% | estimated ± 8.7 pp, medium confidence |
| ExploitBench | 31.3% | estimated ± 12.6 pp, low confidence |
| ExploitGym | 31.7% | estimated ± 9.2 pp, low confidence |
| C-Eval | 94.8% | estimated ± 0.9 pp, low confidence |
| Claw-Eval | 72.6% | estimated ± 6.3 pp, low confidence |
| DeepPlanning | 51.5% | estimated ± 13.1 pp, low confidence |
| INCLUDE | 88.8% | estimated ± 2.0 pp, medium confidence |
| MCP Atlas | 83.0% | measured |
| MMLU-ProX | 90.7% | estimated ± 1.3 pp, medium confidence |
| MMLU-Redux | 95.7% | estimated ± 2.1 pp, high confidence |
| NL2Repo | 56.4% | estimated ± 6.0 pp, medium confidence |
| PostTrainBench v1 | 34.3% | estimated ± 4.6 pp, high confidence |
| QwenClawBench | 68.4% | estimated ± 2.6 pp, medium confidence |
| SuperGPQA | 77.5% | estimated ± 7.2 pp, medium confidence |
| Toolathlon | 62.8% | estimated ± 4.2 pp, high confidence |
| HealthBench Hard | 32.1% | estimated ± 8.6 pp, low confidence |
| LiveCodeBench Pro | 90.1% | estimated ± 6.0 pp, low confidence |
| React Native Evals | 78.4% | estimated ± 4.7 pp, medium confidence |
| ResearchClawBench | 19.6% | estimated ± 1.8 pp, high confidence |
| PostTrainBench | 28.9% | estimated ± 3.7 pp, high confidence |
| DAYJOB | 2.1% | estimated ± 3.2 pp, high confidence |
| DAYJOB Healthcare | 0.9% | estimated ± 4.7 pp, high confidence |
| Finance Agent v2 | 57.9% | measured |
| BioMysteryBench (human-solvable) | 88.8% | estimated ± 0.6 pp, medium confidence |
| FrontierCode 1.1 Extended | 58.6% | estimated ± 3.0 pp, medium confidence |
| HealthBench (raw) | 48.2% | estimated ± 6.0 pp, medium confidence |
| HealthBench (length-adjusted) | 60.3% | estimated ± 2.2 pp, high confidence |
| HealthBench Professional | 65.4% | measured |
| HealthBench Professional (raw) | 58.8% | estimated ± 4.5 pp, high confidence |
| HLE-Verified | 3.6% | estimated ± 6.8 pp, low confidence |
| LABBench2 | 79.5% | estimated ± 2.4 pp, low confidence |
| ScarfBench | 63.0% | estimated ± 3.8 pp, medium confidence |
| Agents' Last Exam | 29.9% | estimated ± 3.1 pp, high confidence |
| OpenHarmony Bench v1.0 | 58.9% | estimated ± 2.4 pp, high confidence |
| SEC-Bench Pro | 49.7% | estimated ± 9.3 pp, medium confidence |
| MRCRv2 | 85.9% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 61.5% | estimated ± 2.6 pp, low confidence |
| BioBasicsBench | 33.9% | estimated ± 2.8 pp, medium confidence |
| LifeVal | 80.5% | estimated ± 1.6 pp, medium confidence |
| ExploitBench Internal Port | 0.0% | estimated ± 6.8 pp, low confidence |
| PinchBench | 90.8% | estimated ± 3.6 pp, low confidence |
| SWE-Atlas Codebase QnA | 64.5% | measured |