Llama 4 Maverick 17B Instruct vs Magistral Small vs Magistral Small 1.2

Llama 4 Maverick 17B Instruct is the better all-round choice, scoring 58/100 against Magistral Small 1.2 (53) and Magistral Small (50). It leads on price and context window. Magistral Small 1.2 wins on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Llama 4 Maverick 17B Instruct is cheaper at $0.321 input / $0.91 output per million tokens (median across 6 API providers). Magistral Small costs $0.50 input / $1.50 output per million tokens (median across 1 API provider); Magistral Small 1.2 costs $0.50 input / $1.50 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.468 per million tokens for Llama 4 Maverick 17B Instruct versus $0.75 for Magistral Small (1.6× as much) and $0.75 for Magistral Small 1.2 (1.6× as much).

Magistral Small scores higher on the Capabilities Index (ECI): Magistral Small 133.2 (#120 of 148), Llama 4 Maverick 17B Instruct 132.2 (#122 of 148) and Magistral Small 1.2 131.4 (#124 of 148). The confidence ranges of the top two overlap (128.9–134.4 vs 128.0–134.1), so treat the gap as small. On individual benchmarks: GPQA Diamond — Llama 4 Maverick 17B Instruct 67.0%, Magistral Small 56.1%, Magistral Small 1.2 47.6%; OTIS Mock AIME 2024–2025 — Magistral Small 30.0%, Magistral Small 1.2 28.1%, Llama 4 Maverick 17B Instruct 20.6%.

There are no published SWE-bench Verified results for Llama 4 Maverick 17B Instruct, Magistral Small and Magistral Small 1.2 yet, so there is no like-for-like coding score. On overall capability, Magistral Small leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.

Llama 4 Maverick 17B Instruct has the largest context window at 1,000,000 tokens, against 131,072 for Magistral Small and 131,072 for Magistral Small 1.2. Maximum output per response: Llama 4 Maverick 17B Instruct up to 16,384, Magistral Small up to 8,192, Magistral Small 1.2 up to 131,072 tokens.

Llama 4 Maverick 17B Instruct accepts text and images; Magistral Small accepts text; Magistral Small 1.2 accepts text and images. Llama 4 Maverick 17B Instruct handles the widest range of inputs.

Yes, all three publish their weights (Apache 2.0), so you can self-host them.

Magistral Small 1.2 is the newest, released Sep 18, 2025. Magistral Small came out Jun 10, 2025; Llama 4 Maverick 17B Instruct came out Apr 5, 2025. Knowledge cutoff: Llama 4 Maverick 17B Instruct Aug 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.