Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Math Reasoning on AIME 25 (Pass@8)
Loading...
80
Pass@8
RFT
66.168
69.759
73.35
76.941
Apr 13, 2026
Pass@8
Updated 4d ago
Evaluation Results
Method
Method
Links
Pass@8
RFT
Base Model=Qwen3-4B-In...
2026.04
80
SRT
Base Model=Qwen3-4B-In...
2026.04
80
SD-ZERO
Base Model=Qwen3-4B-In...
2026.04
80
SD-ZERO
Base Model=Olmo-3-7B-I...
2026.04
80
Qwen3-4B-Instruct
Base Model=Qwen3-4B-In...
2026.04
76.7
SRT
Base Model=Olmo-3-7B-I...
2026.04
76.7
SFT
Base Model=Qwen3-4B-In...
2026.04
73.3
Olmo-3-7B-Instruct
Base Model=Olmo-3-7B-I...
2026.04
73.3
RFT
Base Model=Olmo-3-7B-I...
2026.04
73.3
SDFT
Base Model=Olmo-3-7B-I...
2026.04
73.3
GRPO
Base Model=Qwen3-4B-In...
2026.04
70
SDFT
Base Model=Qwen3-4B-In...
2026.04
70
SFT
Base Model=Olmo-3-7B-I...
2026.04
66.7
GRPO
Base Model=Olmo-3-7B-I...
2026.04
66.7
Feedback
Search any
task
Search any
task