#ModelAccuracyPaper
1w/o Self-Improvement95.95link
2SePO-Generalist95.00link
3w/o Open-Ended Evolution91.10link
4Manual-CoT90.45link
5Jarvis75.95link
6ChatEval75.36link
7Camel75.07link
8AutoGen73.02link
9EvoAgent73.02link
10LLM-debate72.72link
11Single Agent68.32link
MBPP mbpp Leaderboard