Other · model
Ling 3.0 Flash FP8 benchmark scores
As of 2026-10-07, Ling 3.0 Flash FP8 (Other) has measured scores on 14 benchmarks and estimated scores on 74 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 85.5% | measured |
| AA-HLE | 23.7% | measured |
| AA-SciCode | 42.0% | measured |
| Artificial Analysis Intelligence Index | 20.1% | measured |
| CritPt | 1.7% | measured |
| GDPval-AA | 22.4% | measured |
| GPQA Diamond | 84.0% | measured |
| HLE | 24.8% | estimated ± 8.2 pp, medium confidence |
| IFBench | 73.4% | measured |
| AA-LCR | 73.0% | measured |
| LiveCodeBench v6 | 85.7% | estimated ± 3.1 pp, high confidence |
| AA-Omniscience Accuracy | 18.2% | measured |
| SciCode | 40.4% | measured |
| BrowseComp | 70.7% | estimated ± 9.0 pp, medium confidence |
| HLE w/ tools | 43.1% | estimated ± 6.1 pp, low confidence |
| IFEval | 92.8% | estimated ± 3.5 pp, high confidence |
| LongBench v2 | 61.5% | estimated ± 5.9 pp, medium confidence |
| τ²-bench results | 91.3% | estimated ± 13.3 pp, low confidence |
| AA Coding Index | 50.6% | measured |
| APEX-Agents | 20.8% | estimated ± 10.0 pp, low confidence |
| APEX-Agents-AA | 19.2% | estimated ± 9.1 pp, medium confidence |
| BioMysteryBench (human-difficult) | 25.4% | estimated ± 5.9 pp, low confidence |
| DeepSearchQA | 84.9% | estimated ± 4.5 pp, high confidence |
| SWE-bench Verified | 76.8% | estimated ± 5.5 pp, medium confidence |
| AutomationBench | 28.4% | estimated ± 9.7 pp, low confidence |
| BFCL v4 | 73.4% | estimated ± 2.6 pp, high confidence |
| CyberGym | 61.7% | estimated ± 5.3 pp, low confidence |
| JobBench | 17.8% | estimated ± 8.6 pp, medium confidence |
| SWE-bench Pro | 52.6% | estimated ± 6.0 pp, medium confidence |
| WideResearch | 72.6% | estimated ± 9.1 pp, low confidence |
| AA Agentic Index | 21.0% | measured |
| MMLU-Pro | 84.7% | estimated ± 3.0 pp, high confidence |
| GPQA | 84.0% | measured |
| AA-IFBench | 59.7% | estimated ± 8.5 pp, medium confidence |
| Gert Labs | 52.8% | estimated ± 8.5 pp, medium confidence |
| AA-AnalystAgent | 15.4% | estimated ± 12.0 pp, low confidence |
| AA EnterpriseOps-Gym | 32.9% | estimated ± 6.7 pp, low confidence |
| AA Harvey LAB | 81.4% | estimated ± 1.2 pp, low confidence |
| ARC-AGI-1 | 78.7% | estimated ± 2.7 pp, medium confidence |
| ARC-AGI-2 | 37.6% | estimated ± 10.1 pp, low confidence |
| CursorBench 3.1 | 24.3% | estimated ± 3.4 pp, low confidence |
| CursorBench 3.2 | 35.5% | estimated ± 4.4 pp, medium confidence |
| FrontierCode 1.1 Main | 21.6% | estimated ± 3.8 pp, medium confidence |
| FrontierSWE v2 | 0.0% | estimated ± 14.6 pp, low confidence |
| OSWorld-Verified | 67.3% | estimated ± 8.7 pp, low confidence |
| Vals GPQA Diamond | 83.1% | estimated ± 2.0 pp, medium confidence |
| Vals LiveCodeBench | 83.9% | estimated ± 0.8 pp, low confidence |
| Vals MMLU-Pro | 80.0% | estimated ± 1.2 pp, high confidence |
| Vals SWE-bench | 64.4% | estimated ± 5.3 pp, low confidence |
| AA AutomationBench | 3.9% | estimated ± 7.0 pp, medium confidence |
| GDP.pdf | 9.4% | estimated ± 5.4 pp, medium confidence |
| AA Tau3 Banking | 22.0% | estimated ± 5.8 pp, medium confidence |
| CursorBench 4.0 | 16.4% | estimated ± 1.6 pp, medium confidence |
| CWE-bench v1 | 32.1% | estimated ± 6.9 pp, low confidence |
| DeepSWE | 15.1% | estimated ± 6.4 pp, low confidence |
| HLE w/o tools | 17.7% | estimated ± 4.4 pp, high confidence |
| PostTrainBench v1.1 | 11.0% | estimated ± 6.1 pp, low confidence |
| Toolathlon-Verified | 49.5% | estimated ± 2.3 pp, low confidence |
| Vibe Code Bench | 22.9% | estimated ± 10.3 pp, low confidence |
| ExploitGym | 0.0% | estimated ± 12.2 pp, low confidence |
| C-Eval | 89.7% | estimated ± 0.9 pp, low confidence |
| Claw-Eval | 64.1% | estimated ± 13.6 pp, low confidence |
| MCP Atlas | 65.0% | estimated ± 7.8 pp, low confidence |
| MMLU-Redux | 92.6% | estimated ± 1.1 pp, medium confidence |
| NL2Repo | 36.6% | estimated ± 5.1 pp, medium confidence |
| QwenClawBench | 55.9% | estimated ± 6.0 pp, low confidence |
| SuperGPQA | 61.6% | estimated ± 7.5 pp, medium confidence |
| Toolathlon | 33.1% | estimated ± 6.3 pp, medium confidence |
| HealthBench Hard | 0.0% | estimated ± 5.1 pp, low confidence |
| MedXpertQA (Text) | 39.8% | estimated ± 4.5 pp, low confidence |
| MMLU-Pro (Arcee) | 84.8% | estimated ± 3.4 pp, medium confidence |
| React Native Evals | 76.8% | estimated ± 3.5 pp, high confidence |
| ResearchClawBench | 16.7% | estimated ± 2.0 pp, high confidence |
| SWE-Rebench | 58.1% | estimated ± 8.9 pp, low confidence |
| ARC-AGI-3 | 0.0% | estimated ± 2.1 pp, medium confidence |
| BioMysteryBench (human-solvable) | 81.7% | estimated ± 0.6 pp, low confidence |
| DRACO | 70.7% | estimated ± 3.0 pp, medium confidence |
| FrontierCode 1.1 Extended | 44.5% | estimated ± 3.4 pp, low confidence |
| HealthBench (raw) | 32.3% | estimated ± 6.4 pp, low confidence |
| HealthBench (length-adjusted) | 53.9% | estimated ± 3.7 pp, low confidence |
| HealthBench Professional | 38.6% | estimated ± 4.8 pp, low confidence |
| HealthBench Professional (raw) | 44.0% | estimated ± 5.0 pp, low confidence |
| HLE-Verified | 15.3% | estimated ± 2.0 pp, low confidence |
| LABBench2 | 70.3% | estimated ± 1.8 pp, low confidence |
| LiveCodeBench | 100.0% | estimated ± 8.9 pp, low confidence |
| OpenHarmony Bench | 51.0% | estimated ± 2.4 pp, medium confidence |
| MMMLU | 87.2% | estimated ± 1.1 pp, medium confidence |
| MMLU | 84.9% | estimated ± 1.1 pp, medium confidence |