Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Agent Path Finding on 3-agent Sum (evaluation set)
Loading...
51.67
Valid Rate
Qwen3-4B + GRPO + Ours
13.3564
23.3032
33.25
43.1968
Jun 16, 2026
Valid Rate
Optimal Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Valid Rate
Optimal Rate
Qwen3-4B + GRPO + Ours
Backbone=Qwen3-4B, Tra...
2026.06
51.67
31.67
Kimi-K2.5
2026.06
46.17
29.25
Qwen3-4B + GRPO (random)
Backbone=Qwen3-4B, Tra...
2026.06
40.42
26.08
Grok-4.2
2026.06
33.42
21
GPT-5.4
2026.06
32.5
20.58
Gemini-3.1-Pro
2026.06
24.5
15.33
Qwen3-4B (base)
Backbone=Qwen3-4B
2026.06
14.83
14
Feedback
Search any
task
Search any
task