Pick a winner in each dimension — change your vote anytime.
Pricing and capabilities synced from the OpenRouter catalogue. Scores are editorial (0–10).
Choose GLM 4.7 if you want gLM users wanting a small step up from 4.6. Choose Mistral Large 3 if you want general-purpose open-weight agent work, especially in the EU.
In our editorial scoring, GLM 4.7 leads in 1 of five dimensions (agentic ability), while Mistral Large 3 leads in 0. On price, GLM 4.7 runs about $0.81 per 1M tokens (blended) and is open-weight; Mistral Large 3 is about $0.80 and open-weight.
The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.