Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Accuracy on GPQA (Scientific Reasoning)
Loading...
48
Accuracy
Qwen3-8B-GRLO+RLVR
17.008
25.054
33.1
41.146
May 14, 2026
Accuracy
Updated 16d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen3-8B-GRLO+RLVR
Backbone=Qwen3-8B, Tra...
2026.05
48
Qwen3-8B-GRLO
Backbone=Qwen3-8B, Tra...
2026.05
47
Qwen3-8B (Non-thinking)
Backbone=Qwen3-8B, Tra...
2026.05
45
Qwen3-8B-RLVR
Backbone=Qwen3-8B, Tra...
2026.05
41.9
Qwen3-8B-Base
Backbone=Qwen3-8B, Tra...
2026.05
25.8
Qwen3-8B-MathSFT
Backbone=Qwen3-8B, Tra...
2026.05
18.2
Feedback
Search any
task
Search any
task