Qwen2.5 7B Instruct vs Ministral 3B vs Mistral Nemo

It is close. Our weighted score puts them within 2 points (Ministral 3B 49/100, Mistral Nemo 48/100, Qwen2.5 7B Instruct 44/100), so choose by what matters most for your work: Mistral Nemo for raw capability, Ministral 3B on price and Qwen2.5 7B Instruct for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Ministral 3B is cheaper at $0.10 input / $0.10 output per million tokens (median across 1 API provider). Mistral Nemo costs $0.15 input / $0.15 output per million tokens (official Mistral API price); Qwen2.5 7B Instruct costs $0.175 input / $0.70 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.10 per million tokens for Ministral 3B versus $0.15 for Mistral Nemo (1.5× as much) and $0.306 for Qwen2.5 7B Instruct (3.1× as much).

Mistral Nemo scores higher on the Capabilities Index (ECI): Mistral Nemo 118.7 (#140 of 148), Qwen2.5 7B Instruct 118.5 (#141 of 148) and Ministral 3B 118.1 (#144 of 148). The confidence ranges of the top two overlap (111.3–121.5 vs 110.7–121.3), so treat the gap as small. On individual benchmarks: GPQA Diamond — Qwen2.5 7B Instruct 35.5%, Mistral Nemo 29.9%, Ministral 3B 25.3%.

There are no published SWE-bench Verified results for Qwen2.5 7B Instruct, Ministral 3B and Mistral Nemo yet, so there is no like-for-like coding score. On overall capability, Mistral Nemo leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.

Qwen2.5 7B Instruct has the largest context window at 131,072 tokens, against 128,000 for Ministral 3B and 128,000 for Mistral Nemo. Maximum output per response: Qwen2.5 7B Instruct up to 8,192, Ministral 3B up to 8,192, Mistral Nemo up to 128,000 tokens.

Qwen2.5 7B Instruct accepts text; Ministral 3B accepts text; Mistral Nemo accepts text. They handle the same number of input types.

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

Ministral 3B is the newest, released Oct 16, 2024. Qwen2.5 7B Instruct came out Sep 19, 2024; Mistral Nemo came out Jul 1, 2024. Knowledge cutoff: Qwen2.5 7B Instruct Apr 2024, Ministral 3B Mar 2024, Mistral Nemo Jul 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.