Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Knowledge Reasoning on HLE
Loading...
4.45
Accuracy
VRPO
2.474
2.987
3.5
4.013
Aug 5, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
VRPO
Optimization Type=test...
2025.08
4.45
VRPO
Base Model=Qwen2.5-7B-...
2025.08
3.94
VRPO
Base Model=Qwen3-8B
2025.08
3.89
GRPO
Optimization Type=test...
2025.08
3.8
λ-GRPO
Base Model=Qwen3-8B
2025.08
3.57
PPO
Optimization Type=test...
2025.08
3.56
λ-GRPO
Base Model=Qwen2.5-7B-...
2025.08
3.34
Base
Base Model=Qwen2.5-7B-...
2025.08
3.29
KTAE
Base Model=Qwen2.5-7B-...
2025.08
3.24
Base
Base Model=Qwen3-8B
2025.08
2.89
KTAE
Base Model=Qwen3-8B
2025.08
2.64
Cold Start
Optimization Type=test...
2025.08
2.55
Feedback
Search any
task
Search any
task
