Category Score V3 leaderboard
LMSpeed Best Models for AI Agents
Compare the best AI models for agents across planning, tool use, environment execution, and recovery benchmarks. Formal ranks use LMSpeed Category Score V3 evidence and uncertainty rules.
Methodology 3.0
Current answer
Among the currently visible formally ranked models, GPT-5.6 Sol has the highest position at global rank 1. Its Category Score is 70.5, with an 80% uncertainty range of ±7.6. 48 visible models have a formal rank. This result applies only to this score run.
Rankings can change when data or methods change. The run date appears above.
Available leaderboard data
- Models shown
- 100
- Formally ranked models
- 48
- Benchmark columns
- 27
- Dimensions with evidence
- 4/4