Other · model
LLaDA2.2-flash benchmark scores
As of 2026-10-07, LLaDA2.2-flash (Other) has measured scores on 7 benchmarks and estimated scores on 43 more.
| Benchmark | Score | Source |
|---|---|---|
| AA-SciCode | 34.7% | estimated ± 3.8 pp, high confidence |
| GDPval-AA | 3.0% | estimated ± 5.8 pp, medium confidence |
| LiveCodeBench v6 | 76.5% | estimated ± 2.1 pp, high confidence |
| SciCode | 33.0% | estimated ± 3.8 pp, high confidence |
| BrowseComp | 59.0% | estimated ± 8.4 pp, medium confidence |
| HLE w/ tools | 23.9% | estimated ± 7.2 pp, low confidence |
| VITA-Bench | 32.6% | estimated ± 9.9 pp, low confidence |
| τ²-bench results | 80.3% | measured |
| AA Coding Index | 23.8% | estimated ± 5.1 pp, medium confidence |
| APEX-Agents | 6.8% | estimated ± 0.6 pp, low confidence |
| APEX-Agents-AA | 20.4% | estimated ± 5.7 pp, medium confidence |
| SWE-bench Verified | 49.3% | measured |
| BFCL v4 | 60.8% | measured |
| CyberGym | 58.4% | estimated ± 9.9 pp, medium confidence |
| JobBench | 22.7% | estimated ± 6.8 pp, medium confidence |
| SWE-bench Pro | 30.1% | measured |
| τ³-bench results | 69.3% | estimated ± 1.8 pp, medium confidence |
| AA Agentic Index | 20.6% | estimated ± 5.1 pp, medium confidence |
| Gert Labs | 53.2% | estimated ± 8.2 pp, low confidence |
| AA EnterpriseOps-Gym | 23.1% | estimated ± 3.6 pp, low confidence |
| CursorBench 3.1 | 31.7% | estimated ± 5.6 pp, low confidence |
| CursorBench 3.2 | 3.9% | estimated ± 3.6 pp, medium confidence |
| FrontierCode 1.1 Main | 0.0% | estimated ± 2.7 pp, low confidence |
| FrontierSWE v2 | 0.0% | estimated ± 9.0 pp, low confidence |
| OSWorld-Verified | 60.2% | estimated ± 10.9 pp, low confidence |
| Vals LiveCodeBench | 20.8% | estimated ± 4.7 pp, low confidence |
| Vals SWE-bench | 34.1% | estimated ± 6.8 pp, low confidence |
| AA AutomationBench | 0.0% | estimated ± 13.0 pp, low confidence |
| AA ITBench | 21.5% | estimated ± 3.6 pp, low confidence |
| AA Tau3 Banking | 8.2% | estimated ± 11.8 pp, low confidence |
| CursorBench 4.0 | 12.6% | estimated ± 3.6 pp, medium confidence |
| PostTrainBench v1.1 | 10.6% | estimated ± 4.7 pp, medium confidence |
| SWE Multilingual | 25.0% | measured |
| Toolathlon-Verified | 31.4% | estimated ± 9.3 pp, low confidence |
| Vibe Code Bench | 0.6% | estimated ± 8.1 pp, low confidence |
| Claw-Eval | 64.2% | measured |
| DeepPlanning | 32.3% | estimated ± 13.1 pp, low confidence |
| MCP Atlas | 46.2% | measured |
| MCP-Tasks | 73.8% | estimated ± 0.6 pp, medium confidence |
| MMLU-ProX | 63.2% | estimated ± 1.7 pp, low confidence |
| NL2Repo | 5.4% | estimated ± 6.1 pp, low confidence |
| NOVA-63 | 26.8% | estimated ± 1.6 pp, low confidence |
| QwenClawBench | 53.7% | estimated ± 2.6 pp, high confidence |
| Toolathlon | 37.2% | estimated ± 7.5 pp, medium confidence |
| LiveCodeBench Pro | 54.0% | estimated ± 6.0 pp, low confidence |
| ResearchClawBench | 17.5% | estimated ± 1.3 pp, high confidence |
| SWE-Rebench | 57.0% | estimated ± 3.6 pp, low confidence |
| FrontierCode 1.1 Extended | 41.5% | estimated ± 3.0 pp, low confidence |
| LiveCodeBench | 63.9% | estimated ± 10.2 pp, low confidence |
| OpenHarmony Bench | 53.3% | estimated ± 4.9 pp, low confidence |