🏆 #1 on MLE-Bench Leaderboard

ML-Master 2.0

Next-generation AI-for-AI agent achieving breakthrough performance through deep integration of exploration and reasoning

Massive Performance Gains

ML-Master 2.0 achieves significant improvements across all complexity levels, with an overall performance increase of 92.7%

Overall (All %)

29.33%
ML-Master 1.0
56.44%
ML-Master 2.0
🚀 +92.7% Improvement

Low Complexity

48.48%
ML-Master 1.0
75.76%
ML-Master 2.0
📈 +56.2% Improvement

Medium Complexity

20.18%
ML-Master 1.0
50.88%
ML-Master 2.0
+152.2% Improvement

High Complexity

24.44%
ML-Master 1.0
42.22%
ML-Master 2.0
💪 +72.8% Improvement

State-of-the-Art Performance

Detailed performance comparison between ML-Master 2.0 and other agents across all task complexity levels

Performance Comparison: Top Methods on MLE-Bench

Performance (%)
75
50
25
0
Low
Medium
High
Overall
Task Complexity Levels
ML-Master 1.0
AIRA-dojo (Meta)
R&D-Agent (Microsoft)
CAIR MLE-STAR-Pro-1.5 (Google)
ML-Master 2.0 (Ours)

ML-Master 2.0 achieves significant improvements across all complexity levels

🎯 Most remarkable improvement in medium complexity tasks at 152.2%

⚡ Overall performance increased from 29.33% to 56.44%, a 92.7% improvement

🏆 MLE-Bench Leaderboard

Rank & Agent LLM Low == Lite (%) Medium (%) High (%) All (%) Runtime (h)
1
ML-Master 2.0
DeepSeek-V3.2-Speciale 75.76 ± 1.24 50.88 ± 2.86 42.22 ± 1.81 56.44 ± 2.02 24
2
Leeroo
Gemini-3-Pro-Preview 68.18 ± 2.62 44.74 ± 1.52 40.00 ± 0.00 50.67 ± 1.33 24
3
Thesis
gpt-5-codex 65.15 ± 1.52 45.61 ± 7.18 31.11 ± 2.22 48.44 ± 3.64 24
4
CAIR MLE-STAR-Pro-1.5
Gemini-2.5-Pro 68.18 ± 2.62 34.21 ± 1.52 33.33 ± 0.00 44.00 ± 1.33 24
5
FM Agent
Gemini-2.5-Pro 62.12 ± 1.52 36.84 ± 1.52 33.33 ± 0.00 43.56 ± 0.89 24
6
Operand ensemble
gpt-5 63.64 ± 0.00 33.33 ± 0.88 20.00 ± 0.00 39.56 ± 0.44 24
7
CAIR MLE-STAR-Pro-1.0
Gemini-2.5-Pro 66.67 ± 1.52 25.44 ± 0.88 31.11 ± 2.22 38.67 ± 0.77 12
8
InternAgent
deepseek-r1 62.12 ± 3.03 26.32 ± 2.63 24.44 ± 2.22 36.44 ± 1.18 12
9
R&D-Agent
gpt-5 68.18 ± 2.62 21.05 ± 1.52 22.22 ± 2.22 35.11 ± 0.44 12
10
Neo multi-agent
undisclosed 48.48 ± 1.52 29.82 ± 2.32 24.44 ± 2.22 34.22 ± 0.89 36
11
AIRA-dojo
o3 55.00 ± 1.47 21.97 ± 1.17 21.67 ± 1.07 31.60 ± 0.82 24
12
R&D-Agent
o3 + GPT-4.1 51.52 ± 4.01 19.30 ± 3.16 26.67 ± 0.00 30.22 ± 0.89 24
13
ML-Master 1.0
deepseek-r1 48.48 ± 1.52 20.18 ± 2.32 24.44 ± 2.22 29.33 ± 0.77 12
14
R&D-Agent
o1-preview 48.18 ± 1.11 8.95 ± 1.05 18.67 ± 1.33 22.40 ± 0.50 24
15
AIDE
o1-preview 35.91 ± 1.86 8.45 ± 0.43 11.67 ± 1.27 17.12 ± 0.61 24

Generated Code

Explore the code generated by ML-Master 2.0 for various competitions

Choose a Competition:

ML-Master 2.0: Select a Competition
# Select a competition from the dropdown to view the generated code