Knowledge on PHYBench
30.06ScoreLLaDA2.0-flash
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| LLaDA2.0-flash2026.02 | 30.06 | 270 | |
| Qwen3-30B-A3B-Inst-25072026.02 | 29.84 | 100 | |
| LLaDA2.1-flashInference Mode=Q Mode2026.02 | 28.23 | 266 | |
| Ling-flash-2.02026.02 | 27.67 | 100 | |
| LLaDA2.1-flashInference Mode=S Mode2026.02 | 26.04 | 410 | |
| Ling-mini-2.02026.02 | 14.59 | — | |
| LLaDA2.1-minimode=Q Mode2026.02 | 13.05 | 0.0252 | |
| LLaDA2.1-minimode=S Mode2026.02 | 12.75 | 0.0441 | |
| LLaDA2.0-mini2026.02 | 11.7 | 0.0248 | |
| Qwen3-8Bno think=true2026.02 | 9.76 | — |