I am seeing a new ranking of AI models led by Gemini 3 Flash. According to the PinchBench benchmark, Gemini 3 Flash topped in OpenClaw tasks with a success rate of 95.1%.



In second and third place are minimax-m2.1 (93.6%) and kimi-k2.5 (93.4%). Claude Sonnet 4.5 is at 92.7%, while GPT-4o is at 85.2%. The difference is noticeable between these models.

Magma's CISO 23pads shared this data. The performance of these AI models varies quite a bit in agent tasks. Gemini's lead is clear for now.
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pin