Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Agent Path Finding on 3-agent 6x6 (evaluation set)
Loading...
52.67
Valid Rate
Qwen3-4B + GRPO + Ours
8.99
20.33
31.67
43.01
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
52.67
37.33
Kimi-K2.5
2026.06
47.33
34.67
Qwen3-4B + GRPO (random)
Backbone=Qwen3-4B, Tra...
2026.06
42.67
26
Grok-4.2
2026.06
35.33
21.33
GPT-5.4
2026.06
28
16
Gemini-3.1-Pro
2026.06
24
12
Qwen3-4B (base)
Backbone=Qwen3-4B
2026.06
10.67
10.67
Feedback
Search any
task
Search any
task