Codestral vs Qwen2.5-VL 7B Instruct vs Command R

It is close. Our weighted score puts them within a point (Qwen2.5-VL 7B Instruct 51/100, Command R 51/100, Codestral 48/100), so choose by what matters most for your work: Command R 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.

Command R is cheaper at $0.15 input / $0.60 output per million tokens (official Cohere API price). Codestral costs $0.30 input / $0.90 output per million tokens (official Mistral API price); Qwen2.5-VL 7B Instruct costs $0.35 input / $1.05 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.263 per million tokens for Command R versus $0.45 for Codestral (1.7× as much) and $0.525 for Qwen2.5-VL 7B Instruct (2× as much).

There is no independent benchmark that covers all three models yet. Codestral has not been scored yet, Qwen2.5-VL 7B Instruct has not been scored yet and Command R has not been scored yet.

There are no published SWE-bench Verified results for Codestral, Qwen2.5-VL 7B Instruct and Command R 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.

Codestral has the largest context window at 256,000 tokens, against 131,072 for Qwen2.5-VL 7B Instruct and 128,000 for Command R. Maximum output per response: Codestral up to 4,096, Qwen2.5-VL 7B Instruct up to 8,192, Command R up to 4,000 tokens.

Codestral accepts text; Qwen2.5-VL 7B Instruct accepts text and images; Command R accepts text. Qwen2.5-VL 7B Instruct handles the widest range of inputs.

Yes, all three publish their weights, so you can self-host them.

Qwen2.5-VL 7B Instruct is the newest, released Sep 2024. Command R came out Aug 30, 2024; Codestral came out May 29, 2024. Knowledge cutoff: Codestral Oct 2024, Qwen2.5-VL 7B Instruct Apr 2024, Command R Jun 1, 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.