Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Nash equilibrium computation on Zero-sum games 7x7
Loading...
100
Success Rate (s@0.10)
LP Oracle
-4
23
50
77
May 11, 2026
Success Rate (s@0.10)
Pass Rate (pass@1)
Updated 2mo ago
Evaluation Results
Method
Method
Links
Success Rate (s@0.10)
Pass Rate (pass@1)
LP Oracle
2026.05
100
-
SFT
Selection=s@0.10, Numb...
2026.05
32
-
Llama-3-8B SFT
Backbone=Llama-3-8B, S...
2026.05
18
-
VERGE
Selection=s@0.10, Numb...
2026.05
18
-
Maximin (pure)
2026.05
10
-
Uniform
2026.05
4
-
Base
Shots=0
2026.05
0
-
Qwen3-32B
Valid Output Rate=8%
2026.05
0
-
SFT
Selection=pass@1
2026.05
-
12
Llama-3-8B SFT
Backbone=Llama-3-8B, S...
2026.05
-
7
VERGE
Selection=pass@1
2026.05
-
7
Feedback
Search any
task
Search any
task