GLM 5.2 vs Qwen3 235B A22B

Choose GLM 5.2 if you want open-weight coding agents that want a long context. Choose Qwen3 235B A22B if you want self-hosted or ultra-cheap open-weight agents.

In our editorial scoring, Qwen3 235B A22B leads in 3 of five dimensions (speed, value for $ and reliability), while GLM 5.2 leads in 2. On price, GLM 5.2 runs about $1.61 per 1M tokens (blended) and is open-weight; Qwen3 235B A22B is about $0.09 and open-weight.

The model is half the story — the agent is the other half

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.