Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Maze Solving on Maze Hard
Loading...
71.8
RSR
GPT-4 + CoT
37.272
46.236
55.2
64.164
May 5, 2026
RSR
Mean Convergence Depth
Updated 19d ago
Evaluation Results
Method
Method
Links
RSR
Mean Convergence Depth
GPT-4 + CoT
Params=≈1T
2026.05
71.8
6.1
S-AI-Recursive
Params=<10M
2026.05
68.4
11.2
TRM
Params=7M
2026.05
62.3
15.4
MiniTransformer+CoT
Params=8M
2026.05
58.3
15.3
Mamba-7M
Params=≈7-8M
2026.05
55.1
19.2
RWKV-7M
Params=≈7-8M
2026.05
52.6
19.8
S-AI-IoT (spatial)
Params=2M
2026.05
51.2
-
GPT-3.5 (5-shot)
Params=175B
2026.05
38.6
-
Feedback
Search any
task
Search any
task