Qwen2.5-Coder-32B-Instruct vs Codestral vs Aya Expanse 32B

It is close. Our weighted score puts them within 3 points (Codestral 48/100, Qwen2.5-Coder-32B-Instruct 45/100, Aya Expanse 32B 33/100), so choose by what matters most for your work: Codestral on price and Codestral for long inputs. 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.

Codestral is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). Qwen2.5-Coder-32B-Instruct costs $0.43 input / $0.60 output per million tokens (median across 4 API providers); Aya Expanse 32B costs $0.50 input / $1.50 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for Codestral versus $0.473 for Qwen2.5-Coder-32B-Instruct (1.1× as much) and $0.75 for Aya Expanse 32B (1.7× as much).

There is no independent benchmark that covers all three models yet. Qwen2.5-Coder-32B-Instruct has not been scored yet, Codestral has not been scored yet and Aya Expanse 32B has not been scored yet.

There are no published SWE-bench Verified results for Qwen2.5-Coder-32B-Instruct, Codestral and Aya Expanse 32B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Aya Expanse 32B does not support tool calling, which most coding agents need.

Codestral has the largest context window at 256,000 tokens, against 131,072 for Qwen2.5-Coder-32B-Instruct and 128,000 for Aya Expanse 32B. Maximum output per response: Qwen2.5-Coder-32B-Instruct up to 8,192, Codestral up to 4,096, Aya Expanse 32B up to 4,000 tokens.

Qwen2.5-Coder-32B-Instruct accepts text; Codestral accepts text; Aya Expanse 32B accepts text. They handle the same number of input types.

Yes, all three publish their weights (CC-BY-NC-4.0), so you can self-host them.

Qwen2.5-Coder-32B-Instruct is the newest, released Nov 12, 2024. Aya Expanse 32B came out Oct 24, 2024; Codestral came out May 29, 2024. Knowledge cutoff: Codestral Oct 2024.

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 Oct 4, 2026.