Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Factual Reasoning on SampleQA (Accuracy)
Loading...
3.21
Accuracy
VRPO
1.6708
2.0704
2.47
2.8696
Aug 5, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
VRPO
Base Model=Qwen3-8B
2025.08
3.21
KTAE
Base Model=Qwen3-8B
2025.08
3.17
λ-GRPO
Base Model=Qwen2.5-7B-...
2025.08
2.94
Base
Base Model=Qwen3-8B
2025.08
2.89
VRPO
Base Model=Qwen2.5-7B-...
2025.08
2.82
λ-GRPO
Base Model=Qwen3-8B
2025.08
2.77
Base
Base Model=Qwen2.5-7B-...
2025.08
2.36
KTAE
Base Model=Qwen2.5-7B-...
2025.08
1.73
Feedback
Search any
task
Search any
task