agentic
AutomationBench-AA
- #102max of 24147.5%
Leader: Gemini 4 Carbon · 77.8%
DeepSeek · released 2026-04-24
Measured on 99 benchmarks.
Not ranked in this one: too little measured data for its benchmarks. Pick another ranking above.
agentic
Leader: Gemini 4 Carbon · 77.8%
agentic
Leader: Sonnet 5.5 · 1814
economics
Leader: Muse Wonder Full · 32.6%
reasoning
Leader: Gemini 4 Carbon · 69.1%
coding
Leader: Kimi K3.1 · 67.2%