#2
Overall rank
48.0
Podium score
4
Board wins
Sep 2, 2026
Released
Chat
Which model people prefer in blind head-to-head conversations.
Reasoning
Hard questions with checkable answers: science, math, puzzles, expert exams.
Coding
Fixing real repositories, building web apps, editing code.
Vision
Understanding images, charts and documents.
Speed
Output tokens per second on the vendor API.
Price
Blended API price per million tokens, cheapest first.
Usage
What developers actually send tokens to.
More from OpenAI
GPT-6 SolGPT-5.6 SolGPT-5.6 TerraGPT-5.5 Pre ReleaseGPT-5.5 Pro Pre ReleaseGPT-5.5 ProGPT-5.5GPT-5.4
Scores as published by each board on the capture date. Model names and logos belong to their owners; logos via logo.dev.