Mistral Small 3.1 24B vs Ministral 8B Instruct

Mistral Small 3.1 24B is the better all-round choice, scoring 54/100 against Ministral 8B Instruct (42). It leads on capability and inputs & features. Ministral 8B Instruct wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond), because Ministral 8B Instruct has no Capabilities Index score yet.

Ministral 8B Instruct is cheaper at $0.15 input / $0.15 output per million tokens (median across 1 API provider). Mistral Small 3.1 24B costs $0.229 input / $0.436 output per million tokens (median across 2 API providers). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Ministral 8B Instruct versus $0.281 for Mistral Small 3.1 24B (1.9× as much).

Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond): Mistral Small 3.1 24B 47.5% and Ministral 8B Instruct 27.2%. On individual benchmarks: GPQA Diamond — Mistral Small 3.1 24B 47.5%, Ministral 8B Instruct 27.2%.

There are no published SWE-bench Verified results for Mistral Small 3.1 24B and Ministral 8B Instruct yet, so there is no like-for-like coding score. On overall capability, Mistral Small 3.1 24B leads, which tends to carry over to coding, but test on your own codebase. Both support tool calling for agent workflows.

Ministral 8B Instruct has the largest context window at 131,072 tokens, against 128,000 for Mistral Small 3.1 24B. Maximum output per response: Mistral Small 3.1 24B up to 16,384, Ministral 8B Instruct up to 8,192 tokens.

Mistral Small 3.1 24B accepts text and images; Ministral 8B Instruct accepts text. Mistral Small 3.1 24B handles the widest range of inputs.

Yes, both publish their weights (Mistral Research License), so you can self-host them.

Mistral Small 3.1 24B is the newest, released Mar 17, 2025. Ministral 8B Instruct came out Oct 16, 2024. Knowledge cutoff: Mistral Small 3.1 24B Jun 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.