Ministral 8B Instruct vs Mistral Large 2.1 vs Qwen2.5 72B Instruct

Ministral 8B Instruct is the better all-round choice, scoring 42/100 against Mistral Large 2.1 (39) and Qwen2.5 72B Instruct (39). It leads on price. Mistral Large 2.1 wins on capability. 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). Qwen2.5 72B Instruct costs $1.40 input / $5.60 output per million tokens (official Alibaba API price); Mistral Large 2.1 costs $2.00 input / $6.00 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Ministral 8B Instruct versus $2.45 for Qwen2.5 72B Instruct (16× as much) and $3.00 for Mistral Large 2.1 (20× as much).

Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond): Mistral Large 2.1 51.3%, Qwen2.5 72B Instruct 49.2% and Ministral 8B Instruct 27.2%. On individual benchmarks: GPQA Diamond — Mistral Large 2.1 51.3%, Qwen2.5 72B Instruct 49.2%, Ministral 8B Instruct 27.2%.

There are no published SWE-bench Verified results for Ministral 8B Instruct, Mistral Large 2.1 and Qwen2.5 72B Instruct yet, so there is no like-for-like coding score. On overall capability, Mistral Large 2.1 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.

Ministral 8B Instruct, Mistral Large 2.1 and Qwen2.5 72B Instruct share the same 131,072-token context window. Maximum output per response: Ministral 8B Instruct up to 8,192, Mistral Large 2.1 up to 16,384, Qwen2.5 72B Instruct up to 8,192 tokens.

Ministral 8B Instruct accepts text; Mistral Large 2.1 accepts text; Qwen2.5 72B Instruct accepts text. They handle the same number of input types.

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

Mistral Large 2.1 is the newest, released Nov 18, 2024. Ministral 8B Instruct came out Oct 16, 2024; Qwen2.5 72B Instruct came out Sep 19, 2024. Knowledge cutoff: Mistral Large 2.1 Nov 2024, Qwen2.5 72B Instruct Apr 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.