Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on MATH500 (Pass@16)
Loading...
91.4
Pass@16
Qwen2.5-7B + GRPO w/ VERL.
79.336
82.468
85.6
88.732
Sep 28, 2025
Pass@16
Updated 5d ago
Evaluation Results
Method
Method
Links
Pass@16
Qwen2.5-7B + GRPO w/ VERL.
Base Model=Qwen2.5-7B,...
2025.09
91.4
Qwen2.5-7B + PPO w/ VERL.
Base Model=Qwen2.5-7B,...
2025.09
91.4
Qwen2.5-7B + PPO
Base Model=Qwen2.5-7B,...
2025.09
91.2
Qwen2.5-7B + GRPO
Base Model=Qwen2.5-7B,...
2025.09
90.8
Qwen2.5-7B
Base Model=Qwen2.5-7B,...
2025.09
90.6
Llama-3.2-3B-Instruct + PPO w/ VERL.
Base Model=Llama-3.2-3...
2025.09
82.4
Llama-3.2-3B-Instruct + PPO
Base Model=Llama-3.2-3...
2025.09
82.2
Llama-3.2-3B-Instruct + GRPO w/ VERL.
Base Model=Llama-3.2-3...
2025.09
80.6
Llama-3.2-3B-Instruct + GRPO
Base Model=Llama-3.2-3...
2025.09
80.2
Llama-3.2-3B-Instruct
Base Model=Llama-3.2-3...
2025.09
79.8
Feedback
Search any
task
Search any
task