Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Countdown on Countdown 3 (test)
Loading...
95
Reward
A-HPO
34.68
50.34
66
81.66
May 28, 2026
Reward
Updated 5d ago
Evaluation Results
Method
Method
Links
Reward
A-HPO
Model=Qwen2.5-7B-Instr...
2026.05
95
A-HPO
Model=Qwen2.5-7B-Instr...
2026.05
94
GRPO
Model=Qwen2.5-7B-Instr...
2026.05
94
GRPO
Model=Qwen2.5-7B-Instr...
2026.05
93
GRPO
Model=Llama3.1-3B-Inst...
2026.05
93
A-HPO
Model=Llama3.1-3B-Inst...
2026.05
91
A-HPO
Model=Llama3.1-3B-Inst...
2026.05
86
GRPO
Model=Llama3.1-3B-Inst...
2026.05
78
A-HPO
Model=Qwen2.5-1.5B-Ins...
2026.05
51
A-HPO
Model=Qwen2.5-1.5B-Ins...
2026.05
47
GRPO
Model=Qwen2.5-1.5B-Ins...
2026.05
47
GRPO
Model=Qwen2.5-1.5B-Ins...
2026.05
37
Feedback
Search any
task
Search any
task
