Game Playing
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.009Exploitability
4
Jun 24, 2026
0.013Exploitability
4
Jun 24, 2026
64Winrate
4
May 27, 2026
65.25Winrate
4
May 27, 2026
69.5Winrate
4
May 27, 2026
67Winrate
4
May 27, 2026
65.12Winrate
4
May 27, 2026
63.88Winrate
4
May 27, 2026
-21.88Mean Performance
4
Apr 21, 2026
16LLM Win Rate
3
May 26, 2026
14LLM Win Rate
3
May 26, 2026
116.7Median Normalized Score
3
Feb 26, 2026
2Winning Rate
2
Apr 3, 2026
10Winning Rate
2
Apr 3, 2026
21Winning Rate
2
Apr 3, 2026
11.3LLM Win Rate
1
May 26, 2026
54Solly Win %
1
May 4, 2026
55Win Rate (Solly)
1
May 4, 2026
0Winning Rate
1
Apr 3, 2026
—
—Primary metric
0
Feb 26, 2026