Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Sequential Decision Making on Sokoban (val)
Loading...
60.4
Success Rate
EVPO
12.04
24.595
37.15
49.705
Apr 21, 2026
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
EVPO
Backbone=Qwen2.5-3B-In...
2026.04
60.4
StarPO-S
Backbone=Qwen2.5-3B-In...
2026.04
45.5
PPO
Backbone=Qwen2.5-3B-In...
2026.04
31.4
DAPO
Backbone=Qwen2.5-3B-In...
2026.04
16.2
GRPO
Backbone=Qwen2.5-3B-In...
2026.04
15.6
Base LLM
Backbone=Qwen2.5-3B-In...
2026.04
13.9
Feedback
Search any
task
Search any
task