Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on SWE-bench OpenHands
Loading...
3.7
Speedup
Hybrid Verified Decoding
0.7672
1.5286
2.29
3.0514
May 31, 2026
Speedup
Updated 1d ago
Evaluation Results
Method
Method
Links
Speedup
Hybrid Verified Decoding
Target Model=Qwen3-8B,...
2026.05
3.7
Hybrid Verified Decoding
Target Model=Llama3.1-...
2026.05
3.31
Hybrid Verified Decoding
Target Model=Qwen3-8B,...
2026.05
3.21
Hybrid Verified Decoding
Target Model=Llama3.1-...
2026.05
2.6
Hybrid Verified Decoding
Target Model=Qwen3-4B,...
2026.05
2.5
Hybrid Verified Decoding
Target Model=Llama3.1-...
2026.05
2.11
Hybrid Verified Decoding
Target Model=Qwen3-4B,...
2026.05
1.52
Hybrid Verified Decoding
Target Model=Qwen3-8B,...
2026.05
1.28
Hybrid Verified Decoding
Target Model=Llama3.1-...
2026.05
1.26
Hybrid Verified Decoding
Target Model=Qwen3-8B,...
2026.05
1.09
Hybrid Verified Decoding
Target Model=Qwen3-4B,...
2026.05
1.08
Hybrid Verified Decoding
Target Model=Qwen3-4B,...
2026.05
0.88
Feedback
Search any
task
Search any
task