GPT-4o mini vs Mistral Small 3.1 24B vs Qwen2.5 7B Instruct

It is close. Our weighted score puts them within 1 points (GPT-4o mini 56/100, Mistral Small 3.1 24B 55/100, Qwen2.5 7B Instruct 44/100), so choose by what matters most for your work: Mistral Small 3.1 24B for raw capability, GPT-4o mini on price and Qwen2.5 7B Instruct for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

GPT-4o mini is cheaper at $0.15 input / $0.60 output per million tokens (official OpenAI API price). Mistral Small 3.1 24B costs $0.229 input / $0.436 output per million tokens (median across 2 API providers); 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 $0.263 per million tokens for GPT-4o mini versus $0.281 for Mistral Small 3.1 24B (1.1× as much) and $0.306 for Qwen2.5 7B Instruct (1.2× as much).

Mistral Small 3.1 24B scores higher on the Capabilities Index (ECI): Mistral Small 3.1 24B 127.5 (#132 of 148), GPT-4o mini 126.6 (#135 of 148) and Qwen2.5 7B Instruct 118.5 (#141 of 148). The confidence ranges of the top two overlap (122.6–129.4 vs 120.5–128.5), so treat the gap as small. On individual benchmarks: GPQA Diamond — Mistral Small 3.1 24B 47.5%, GPT-4o mini 37.7%, Qwen2.5 7B Instruct 35.5%; OTIS Mock AIME 2024–2025 — GPT-4o mini 6.9%, Mistral Small 3.1 24B 5.8%, Qwen2.5 7B Instruct 2.5%.

There are no published SWE-bench Verified results for GPT-4o mini, Mistral Small 3.1 24B and Qwen2.5 7B 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. 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 GPT-4o mini and 128,000 for Mistral Small 3.1 24B. Maximum output per response: GPT-4o mini up to 16,384, Mistral Small 3.1 24B up to 16,384, Qwen2.5 7B Instruct up to 8,192 tokens.

GPT-4o mini accepts text, images and PDFs; Mistral Small 3.1 24B accepts text and images; Qwen2.5 7B Instruct accepts text. GPT-4o mini handles the widest range of inputs.

Mistral Small 3.1 24B and Qwen2.5 7B Instruct publishes its weights and can be self-hosted; GPT-4o mini is proprietary.

Mistral Small 3.1 24B is the newest, released Mar 17, 2025. Qwen2.5 7B Instruct came out Sep 19, 2024; GPT-4o mini came out Jul 18, 2024. Knowledge cutoff: GPT-4o mini Sep 2023, Mistral Small 3.1 24B Jun 2024, Qwen2.5 7B 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.