GLM-4.5-Air vs Qwen3 Omni 30B A3B Thinking vs Codestral 25.08

Qwen3 Omni 30B A3B Thinking is the better all-round choice, scoring 59/100 against GLM-4.5-Air (48) and Codestral 25.08 (47). It leads on inputs & features. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

GLM-4.5-Air is cheaper at $0.20 input / $1.10 output per million tokens (official Z.AI API price). Qwen3 Omni 30B A3B Thinking costs $0.25 input / $0.97 output per million tokens (median across 1 API provider); Codestral 25.08 costs $0.30 input / $0.90 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.425 per million tokens for GLM-4.5-Air versus $0.43 for Qwen3 Omni 30B A3B Thinking (1× as much) and $0.45 for Codestral 25.08 (1.1× as much).

There is no independent benchmark that covers all three models yet. GLM-4.5-Air has not been scored yet, Qwen3 Omni 30B A3B Thinking has not been scored yet and Codestral 25.08 has not been scored yet.

There are no published SWE-bench Verified results for GLM-4.5-Air, Qwen3 Omni 30B A3B Thinking and Codestral 25.08 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

GLM-4.5-Air has the largest context window at 131,072 tokens, against 128,000 for Codestral 25.08 and 65,536 for Qwen3 Omni 30B A3B Thinking. Maximum output per response: GLM-4.5-Air up to 98,304, Qwen3 Omni 30B A3B Thinking up to 16,384, Codestral 25.08 up to 8,192 tokens.

GLM-4.5-Air accepts text; Qwen3 Omni 30B A3B Thinking accepts text, images, audio and video; Codestral 25.08 accepts text. Qwen3 Omni 30B A3B Thinking handles the widest range of inputs.

GLM-4.5-Air and Qwen3 Omni 30B A3B Thinking publishes its weights (Apache-2.0) and can be self-hosted; Codestral 25.08 is proprietary.

Qwen3 Omni 30B A3B Thinking is the newest, released Sep 22, 2025. Codestral 25.08 came out Jul 30, 2025; GLM-4.5-Air came out Jul 28, 2025. Knowledge cutoff: GLM-4.5-Air Apr 2025.

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 2, 2026.