Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Maze Navigation on Maze
Loading...
100
RSR
Optimal
36.144
52.722
69.3
85.878
Jun 20, 2025
Aug 12, 2025
Oct 4, 2025
Nov 26, 2025
Jan 18, 2026
Mar 12, 2026
May 5, 2026
RSR
Time Taken (t*)
Average Steps
Updated 18d ago
Evaluation Results
Method
Method
Links
RSR
Time Taken (t*)
Average Steps
Optimal
2025.06
100
-
25.224
PPO
2025.06
99.64
-
27.23
MPPO
variant=A
2025.06
99.52
-
27.649
MPPO
variant=B
2025.06
99.04
-
28.104
Bot A
2025.06
92.4
-
53.45
Bot B
2025.06
89
-
55.714
GPT-4+CoT
Parameters=≈1T
2026.05
71.8
6.1
-
S-AI-Recursive
Parameters=<10M
2026.05
68.4
11.2
-
TRM
Parameters=7M
2026.05
62.3
15.4
-
S-AI-IoT
Parameters=2M
2026.05
51.2
-
-
GPT-3.5
Parameters=175B
2026.05
38.6
-
-
Feedback
Search any
task
Search any
task