Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Agentic Task on Delegate-52
Loading...
3.46
Speedup
Hybrid Verified Decoding
0.704
1.4195
2.135
2.8505
May 31, 2026
Speedup
Updated 1d ago
Evaluation Results
Method
Method
Links
Speedup
Hybrid Verified Decoding
Target Model=Llama3.1-...
2026.05
3.46
Hybrid Verified Decoding
Target Model=Qwen3-4B,...
2026.05
3.4
Hybrid Verified Decoding
Target Model=Llama3.1-...
2026.05
3.38
Hybrid Verified Decoding
Target Model=Qwen3-8B,...
2026.05
3.25
Hybrid Verified Decoding
Target Model=Qwen3-8B,...
2026.05
2.14
Hybrid Verified Decoding
Target Model=Qwen3-4B,...
2026.05
1.9
Hybrid Verified Decoding
Target Model=Qwen3-4B,...
2026.05
1.64
Hybrid Verified Decoding
Target Model=Qwen3-8B,...
2026.05
1.44
Hybrid Verified Decoding
Target Model=Llama3.1-...
2026.05
1.24
Hybrid Verified Decoding
Target Model=Qwen3-4B,...
2026.05
1.18
Hybrid Verified Decoding
Target Model=Qwen3-8B,...
2026.05
1.06
Hybrid Verified Decoding
Target Model=Llama3.1-...
2026.05
0.81
Feedback
Search any
task
Search any
task