Code on LiveCodeBench v6 (Pass@1)
67.3Pass@1Mercury-2
Evaluation Results
| Method | Links | |
|---|---|---|
| Mercury-2Params=Commercial, Sampling mode=Diffusion2026.06 | 67.3 | |
| FLARE-9BParams=9B, Sampling mode=AR-Trust2026.06 | 49.71 | |
| Qwen3.5-9BParams=9B, Sampling mode=AR2026.06 | 49.71 | |
| LLaDA-2.1-flashParams=100B-A5B, Sampling mode=Diffusion2026.06 | 44.05 | |
| LLaDA-2.0-flashParams=100B-A5B, Sampling mode=Diffusion2026.06 | 42.29 | |
| LLaDA-2.0-miniParams=16B-A1B, Sampling mode=Diffusion2026.06 | 31.5 | |
| LLaDA-2.1-miniParams=16B-A1B, Sampling mode=Diffusion2026.06 | 28.85 | |
| SDAR 30B-A3BParams=30B-A3B, Sampling mode=Diffusion2026.06 | 21.7 | |
| FLARE-9BParams=9B, Sampling mode=Diffusion-Trust2026.06 | 5.71 |