Other · model
Ling 3.0 Flash Sante benchmark scores
As of 2026-10-29, Ling 3.0 Flash Sante (Other) has measured scores on 7 benchmarks and estimated scores on 50 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-GPQA Diamond | 91.5% | estimated ± 2.1 pp, medium confidence |
| GDPval-AA | 46.1% | estimated ± 7.7 pp, medium confidence |
| GPQA Diamond | 88.8% | estimated ± 0.9 pp, medium confidence |
| AA-LCR | 70.5% | measured |
| BrowseComp | 80.2% | measured |
| HLE w/ tools | 57.1% | measured |
| LongBench v2 | 60.4% | estimated ± 5.8 pp, low confidence |
| VITA-Bench | 44.9% | estimated ± 6.7 pp, low confidence |
| τ²-bench results | 98.1% | estimated ± 3.1 pp, high confidence |
| APEX-Agents | 30.3% | estimated ± 0.6 pp, medium confidence |
| APEX-Agents-AA | 26.8% | estimated ± 4.2 pp, high confidence |
| DeepSearchQA | 90.8% | measured |
| AutomationBench | 29.5% | estimated ± 10.5 pp, low confidence |
| BFCL v4 | 74.6% | estimated ± 4.7 pp, low confidence |
| CyberGym | 72.0% | estimated ± 7.3 pp, medium confidence |
| JobBench | 46.1% | estimated ± 6.4 pp, medium confidence |
| WideResearch | 77.9% | estimated ± 3.5 pp, high confidence |
| AA Agentic Index | 34.2% | estimated ± 8.2 pp, medium confidence |
| GPQA | 92.6% | estimated ± 1.0 pp, medium confidence |
| Gert Labs | 62.1% | estimated ± 7.4 pp, medium confidence |
| AA EnterpriseOps-Gym | 42.8% | estimated ± 3.3 pp, medium confidence |
| AA Harvey LAB v1.0 | 90.1% | estimated ± 1.7 pp, medium confidence |
| AA Tau3 Banking | 35.5% | estimated ± 3.9 pp, high confidence |
| ApprenticeBench | 21.6% | estimated ± 10.1 pp, low confidence |
| MazeBench | 0.0% | estimated ± 6.1 pp, low confidence |
| OSWorld-Verified | 73.1% | estimated ± 5.8 pp, medium confidence |
| Vals GPQA Diamond | 91.1% | estimated ± 1.5 pp, low confidence |
| Vals MMLU-Pro | 84.7% | estimated ± 1.5 pp, low confidence |
| AA AutomationBench | 52.8% | estimated ± 11.6 pp, low confidence |
| CWE-Bench-AA | 57.6% | estimated ± 5.2 pp, medium confidence |
| AA Cyber Index | 37.6% | estimated ± 12.8 pp, low confidence |
| DeepsecBench-AA | 1.5% | estimated ± 6.0 pp, low confidence |
| GDP.pdf | 12.5% | estimated ± 4.9 pp, medium confidence |
| AA ITBench | 45.8% | estimated ± 4.1 pp, high confidence |
| HLE w/o tools | 37.4% | estimated ± 5.0 pp, low confidence |
| OSWorld 2.1 | 63.6% | estimated ± 8.3 pp, low confidence |
| Toolathlon-Verified | 71.9% | estimated ± 5.7 pp, medium confidence |
| ARC-AGI-3 | 2.9% | estimated ± 10.6 pp, low confidence |
| ARC-AGI-3 Provider Adapter | 7.0% | estimated ± 13.7 pp, low confidence |
| Hermes Bench | 68.8% | estimated ± 4.8 pp, medium confidence |
| Hermes Index | 38.4% | estimated ± 10.0 pp, medium confidence |
| ExploitGym | 2.9% | estimated ± 9.2 pp, low confidence |
| Claw-Eval | 69.6% | estimated ± 6.3 pp, low confidence |
| DeepPlanning | 48.0% | estimated ± 13.1 pp, low confidence |
| MCP Atlas | 75.6% | measured |
| QwenClawBench | 62.8% | estimated ± 2.6 pp, high confidence |
| Toolathlon | 49.7% | estimated ± 4.2 pp, high confidence |
| MedXpertQA (Text) | 51.0% | measured |
| ResearchClawBench | 18.7% | estimated ± 1.8 pp, medium confidence |
| DRACO | 78.1% | estimated ± 4.5 pp, medium confidence |
| HealthBench (length-adjusted) | 46.3% | estimated ± 2.2 pp, medium confidence |
| HealthBench Professional | 54.3% | measured |
| HealthBench Professional (raw) | 61.7% | estimated ± 6.1 pp, low confidence |
| Agents' Last Exam | 28.2% | estimated ± 13.0 pp, low confidence |
| MRCRv2 | 76.0% | estimated ± 11.3 pp, low confidence |
| MMLongBench-Doc | 61.0% | estimated ± 2.6 pp, low confidence |
| PinchBench | 90.2% | estimated ± 3.6 pp, medium confidence |