Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reasoning on ace
Loading...
59.7
Pass Rate
GRPO
32.868
39.834
46.8
53.766
May 25, 2026
Pass Rate
Updated 8d ago
Evaluation Results
Method
Method
Links
Pass Rate
GRPO
Model=OLMo-3-7B-Instruct
2026.05
59.7
SRPO
Model=OLMo-3-7B-Instruct
2026.05
59.6
RRPO
Model=OLMo-3-7B-Instruct
2026.05
59
Cr-GRPO
Model=OLMo-3-7B-Instruct
2026.05
50.5
SPO-Tree
Model=OLMo-3-7B-Instruct
2026.05
50.2
Base
Model=OLMo-3-7B-Instruct
2026.05
48.4
SRPO
Model=Qwen2.5-14B-Inst...
2026.05
46.2
RRPO
Model=Qwen2.5-14B-Inst...
2026.05
45.7
GRPO
Model=Qwen2.5-14B-Inst...
2026.05
45.2
Base
Model=Qwen2.5-14B-Inst...
2026.05
44.2
SCoRe
Model=Qwen2.5-14B-Inst...
2026.05
43.7
SPO-Tree
Model=Qwen2.5-14B-Inst...
2026.05
43.1
Cr-GRPO
Model=Qwen2.5-14B-Inst...
2026.05
42.5
SCoRe
Model=OLMo-3-7B-Instruct
2026.05
33.9
Feedback
Search any
task
Search any
task
