Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Agent Path Finding on 3-agent 9x9 (test)
Loading...
44
Valid Rate
Qwen3-4B + GRPO + Ours
8.64
17.82
27
36.18
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
44
25.33
Kimi-K2.5
2026.06
36.67
24.67
Grok-4.2
2026.06
36
22
Qwen3-4B + GRPO (random)
Backbone=Qwen3-4B, Tra...
2026.06
32.67
18.67
GPT-5.4
2026.06
20
11.33
Gemini-3.1-Pro
2026.06
12
9.33
Qwen3-4B (base)
Backbone=Qwen3-4B
2026.06
10
10
Feedback
Search any
task
Search any
task