vis
vis2mo ago

LLM Leaderboard thinking models

btw for the ai leaderboard are these including the thinking models or no https://www.convex.dev/llm-leaderboard
Convex
LLM Leaderboard: Compare top language models for code generation
The LLM Leaderboard compares how large language models perform across various AI Code gen evaluation categories.
1 Reply
Jordan22
Jordan222mo ago
hi! for claude sonnet 4, we don't use the thinking mode and for gemini 2.5 pro, we use the thinking mode. does that answer your question?

Did you find this page helpful?