List your company

Reasoning on WebInstruct

53.96AccuracyCOACT
2.719216.022129.32542.6279Apr 19, 2026

Evaluation results

MethodLinks
COACTBackbone=Qwen3-4B, Iteration=Iteration 42026.0453.96
COACTBackbone=Qwen3-4B, Iteration=Iteration 32026.0452.77
Pref + EntBackbone=Qwen3-4B, Iteration=Iteration 42026.0452.48
Pref CertaintyBackbone=Qwen3-4B, Iteration=Iteration 42026.0451.25
COACTBackbone=Qwen3-4B, Iteration=Iteration 22026.0450.38
Pref + EntBackbone=Qwen3-4B, Iteration=Iteration 32026.0450.21
Pref CertaintyBackbone=Qwen3-4B, Iteration=Iteration 32026.0449.64
Pref CertaintyBackbone=Qwen3-4B, Iteration=Iteration 22026.0447.92
EntropyBackbone=Qwen3-4B, Iteration=Iteration 42026.0447.83
Pref + EntBackbone=Qwen3-4B, Iteration=Iteration 22026.0446.73
EntropyBackbone=Qwen3-4B, Iteration=Iteration 32026.0445.89
COACTBackbone=Qwen3-4B, Iteration=Iteration 12026.0444.23
RandomBackbone=Qwen3-4B, Iteration=Iteration 42026.0444.12
EntropyBackbone=Qwen3-4B, Iteration=Iteration 22026.0443.26
Pref + EntBackbone=Qwen3-4B, Iteration=Iteration 12026.0442.87
RandomBackbone=Qwen3-4B, Iteration=Iteration 32026.0442.37
Pref CertaintyBackbone=Qwen3-4B, Iteration=Iteration 12026.0441.25
RandomBackbone=Qwen3-4B, Iteration=Iteration 22026.0440.15
EntropyBackbone=Qwen3-4B, Iteration=Iteration 12026.0439.14
RandomBackbone=Qwen3-4B, Iteration=Iteration 12026.0437.68
Base ModelBackbone=Qwen3-4B2026.0435.92
COACTBackbone=Llama3-8B, Iteration=Iteration 42026.0415.97
COACTBackbone=Llama3-8B, Iteration=Iteration 22026.0415.38
Pref + EntBackbone=Llama3-8B, Iteration=Iteration 42026.0414.87
Pref CertaintyBackbone=Llama3-8B, Iteration=Iteration 42026.0414.53
COACTBackbone=Llama3-8B, Iteration=Iteration 32026.0413.82
Pref CertaintyBackbone=Llama3-8B, Iteration=Iteration 22026.0413.46
Pref + EntBackbone=Llama3-8B, Iteration=Iteration 32026.0413.08
Pref + EntBackbone=Llama3-8B, Iteration=Iteration 22026.0412.18
Pref CertaintyBackbone=Llama3-8B, Iteration=Iteration 32026.0411.97
COACTBackbone=Llama3-8B, Iteration=Iteration 12026.0411.54
Pref + EntBackbone=Llama3-8B, Iteration=Iteration 12026.0410.26
EntropyBackbone=Llama3-8B, Iteration=Iteration 42026.0410.11
RandomBackbone=Llama3-8B, Iteration=Iteration 42026.049.62
Pref CertaintyBackbone=Llama3-8B, Iteration=Iteration 12026.049.23
EntropyBackbone=Llama3-8B, Iteration=Iteration 32026.048.82
EntropyBackbone=Llama3-8B, Iteration=Iteration 22026.047.93
Base ModelBackbone=Llama3-8B2026.047.69
EntropyBackbone=Llama3-8B, Iteration=Iteration 12026.047.51
RandomBackbone=Llama3-8B, Iteration=Iteration 12026.047.05
RandomBackbone=Llama3-8B, Iteration=Iteration 32026.045.13
RandomBackbone=Llama3-8B, Iteration=Iteration 22026.044.69