List your company

Reasoning on SQuAD 2.0

90.8ScoreLLaDA2.1-flash
74.950479.065283.1887.2948Feb 9, 2026

Evaluation results

MethodLinks
LLaDA2.1-flashInference Mode=Q Mode2026.0290.8390
LLaDA2.1-flashInference Mode=S Mode2026.0290.65501
LLaDA2.0-flash2026.0290310
Qwen3-30B-A3B-Inst-25072026.0289.51100
LLaDA2.0-mini2026.0286.52.47
Qwen3-8Bno think=true2026.0285.21—
LLaDA2.1-minimode=Q Mode2026.0285.133.09
LLaDA2.1-minimode=S Mode2026.0284.514.33
Ling-flash-2.02026.0281.32100
Ling-mini-2.02026.0275.56—