Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Sequential Decision Making on FrozenLake (val)
Loading...
68.4
Success Rate
EVPO
11.096
25.973
40.85
55.727
Apr 21, 2026
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
EVPO
Backbone=Qwen2.5-3B-In...
2026.04
68.4
PPO
Backbone=Qwen2.5-3B-In...
2026.04
61.1
StarPO-S
Backbone=Qwen2.5-3B-In...
2026.04
35.9
GRPO
Backbone=Qwen2.5-3B-In...
2026.04
23.4
DAPO
Backbone=Qwen2.5-3B-In...
2026.04
20.7
Base LLM
Backbone=Qwen2.5-3B-In...
2026.04
13.3
Feedback
Search any
task
Search any
task