Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Legal Reasoning on LEXam
Loading...
23.4
Pass@1 Accuracy
Qwen2.5-7B + PPO w/ VERL.
17.056
18.703
20.35
21.997
Sep 28, 2025
Pass@1 Accuracy
Updated 5d ago
Evaluation Results
Method
Method
Links
Pass@1 Accuracy
Qwen2.5-7B + PPO w/ VERL.
Base Model=Qwen2.5-7B,...
2025.09
23.4
Qwen2.5-7B + GRPO w/ VERL.
Base Model=Qwen2.5-7B,...
2025.09
23
Qwen2.5-7B + PPO
Base Model=Qwen2.5-7B,...
2025.09
22.8
Mathstral-7B-v0.1 + GRPO w/ VERL.
Base Model=Mathstral-7...
2025.09
22.6
Mathstral-7B-v0.1 + GRPO
Base Model=Mathstral-7...
2025.09
22.4
Qwen2.5-7B + GRPO
Base Model=Qwen2.5-7B,...
2025.09
22
Mathstral-7B-v0.1 + PPO w/ VERL.
Base Model=Mathstral-7...
2025.09
21.4
Qwen2.5-7B
Base Model=Qwen2.5-7B
2025.09
21.1
Mathstral-7B-v0.1
Base Model=Mathstral-7...
2025.09
19.6
Mathstral-7B-v0.1 + PPO
Base Model=Mathstral-7...
2025.09
17.3
Feedback
Search any
task
Search any
task