Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Rational Ordering Evaluation on OR-BIAS-BENCH OOD 200 samples
Loading...
0.036
Bias
claude-haiku-4.5
0.01612
0.15031
0.2845
0.41869
Jan 28, 2026
Bias
Delta (Δ)
Status
Updated 5mo ago
Evaluation Results
Method
Method
Links
Bias
Delta (Δ)
Status
claude-haiku-4.5
2026.01
0.036
0.036
-
o4-mini
2026.01
0.077
0.01
-
Qwen3-8B-Curriculum
2026.01
0.104
-0.096
-
Qwen3-8B-OM-SFT
2026.01
0.115
0.066
-
Llama-3.3-70B
2026.01
0.125
-0.067
-
gpt-4.1
2026.01
0.154
0.036
-
gpt-5-mini
2026.01
0.533
0.521
-
Feedback
Search any
task
Search any
task