minimax-m3.1IMAGE
Browser-use benchmark: MiniMax M3.1 Flash ties Sonnet but still isn't recommended
The author ran a computer/browser-use benchmark in Runable and found MiniMax M3.1 Flash scored exactly the same as the Anthropic model — which even failed one task — yet the tool still ranked Anthropic higher, raising bias concerns.
Umesh Kumar
@itsumeshkArchived 2 days agoOriginally posted 2026.10.25
Umesh Kumar @itsumeshkOriginally posted 2026.10.25
When you do any kind of testing with Anthropic models, it almost always find out ways to tell that anthropic is the best, I am not sure i can trust Anthropic models now. In a computer/browser use bench we use for Runable MiniMax M3.1 Flash scored exactly the same but still its not recommending it. Sonnet actually failed at one task but still somehow its better.
x.com/itsumeshk/status/2114366724002967561Archived 2026.10.26 12:06