General chat
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
52Win Rate
12
Mar 6, 2026
82.75Win Rate
12
Mar 6, 2026
68.16LLM Judge Score
12
Mar 6, 2026
1,062.4WB-Elo
12
Feb 26, 2026
61.7Win Rate
6
May 18, 2026
46.5Win Rate
5
May 19, 2026
46.1Win-rate
5
Feb 26, 2026
0.492Win Rate
5
Feb 26, 2026