Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Natural Language Inference on MLGym MNLI
Loading...
92.5
Accuracy
Human Best
82.9632
85.4391
87.915
90.3909
Jun 20, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Human Best
Method Type=Human Base...
2026.06
92.5
ARTS
Base Model=o3
2026.06
84.71
Linear
Method Type=Prior Works
2026.06
84.42
MLEvolve
Method Type=Prior Works
2026.06
84.26
ARTS*
Base Model=Qwen 4B, Te...
2026.06
84.01
AIRA
Method Type=Prior Works
2026.06
83.77
ARTS
Base Model=Qwen 4B
2026.06
83.33
Feedback
Search any
task
Search any
task
