minimax-m3.1IMAGE

RSI Arena report: M3.1 Flash ranks #2 at training another AI, far cheaper than GPT-6 Astra

The RSI Arena team says M3.1 Flash placed second in self-improvement tasks, running experiments, training a model and iterating on human feedback at far lower cost than GPT-6 Astra.

Bake AI

@bake_ai_hqArchived 8 days agoOriginally posted 2026.10.20

RSI Arena report: M3.1 Flash ranks #2 at training another AI, far cheaper than GPT-6 Astra

Bake AI @bake_ai_hqOriginally posted 2026.10.20

Open original on X

We were working on our RSI Arena report when we saw that MiniMax M3.1 Flash launched today. Had to share this one 🐰: #2 with a remarkably lower cost compared to GPT-6 Astra. It really surprised us with how well it could train another AI. It ran experiments, trained a model, then kept improving it with human feedback. We’re wrapping up the technical report and will release all training artifacts and model checkpoints soon! Stay tuned!

x.com/bake_ai_hq/status/2112436813084381238Archived 2026.10.20 20:24