Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Strategic Game Playing on TextArena SPIN-Bench
Loading...
54.9
Win Rate (Simple Negotiation)
MEMO
12.364
23.407
34.45
45.493
Mar 9, 2026
Win Rate (Simple Negotiation)
Win Rate (Two Dollar Game)
Win Rate (Kuhn Poker)
Win Rate (Briscola)
Win Rate (Simple Tak)
Mean Win Rate
Mean RSE
Updated 1mo ago
Evaluation Results
Method
Method
Links
Win Rate (Simple Negotiation)
Win Rate (Two Dollar Game)
Win Rate (Kuhn Poker)
Win Rate (Briscola)
Win Rate (Simple Tak)
Mean Win Rate
Mean RSE
MEMO
Base Model=GPT-4o-mini
2026.03
54.9
52.4
55.6
42.7
41.8
49.5
6.4
MEMO
Base Model=Qwen2.5-7B-...
2026.03
48
48.4
60
31.1
34
44.3
6.1
baseline
Base Model=GPT-4o-mini
2026.03
31.3
32.2
39.1
0.3
21.4
25.1
44.9
MEMO
Base Model=Gemini-2.5-...
2026.03
30
35
58
49
32
40.8
-
baseline
Base Model=Qwen2.5-7B-...
2026.03
24
17.1
45.3
2.8
15.1
20.9
30.1
baseline
Base Model=Gemini-2.5-...
2026.03
14
15
50
32
26
27.4
-
Feedback
Search any
task
Search any
task