Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Out-of-Distribution Generalization Average (GPQA-Diamond, ARC-C, HumanEval)
Loading...
55.35
Pass@1
TARPO
52.4588
53.2094
53.96
54.7106
Jun 4, 2026
Pass@1
Pass@32
Tokens Count
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1
Pass@32
Tokens Count
TARPO
Backbone=Qwen2.5-3B-In...
2026.06
55.35
92.74
337.9
HRPO
Backbone=Qwen2.5-3B-In...
2026.06
54.03
92.22
407.2
GRPO
Backbone=Qwen2.5-3B-In...
2026.06
53.89
91.17
412.2
CoT
Backbone=Qwen2.5-3B-In...
2026.06
53.52
93.79
262.7
Pure Latent
Backbone=Qwen2.5-3B-In...
2026.06
52.67
65.95
254.7
Entropy-Routed
Backbone=Qwen2.5-3B-In...
2026.06
52.57
92.47
243
Feedback
Search any
task
Search any
task