Llama 4 Maverick 17B Instruct vs Mistral Medium 3

Llama 4 Maverick 17B Instruct is the better all-round choice, scoring 58/100 against Mistral Medium 3 (53). It leads on price and context window. Mistral Medium 3 wins on capability. 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). Mistral Medium 3 costs $0.40 input / $2.00 output per million tokens (official Mistral API price). 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 $0.80 for Mistral Medium 3 (1.7× as much).

Mistral Medium 3 scores higher on the Capabilities Index (ECI): Mistral Medium 3 134.1 (#117 of 148) and Llama 4 Maverick 17B Instruct 132.2 (#122 of 148). The confidence ranges of the top two overlap (130.5–135.6 vs 128.0–134.1), so treat the gap as small. On individual benchmarks: GPQA Diamond — Llama 4 Maverick 17B Instruct 67.0%, Mistral Medium 3 59.5%; OTIS Mock AIME 2024–2025 — Mistral Medium 3 32.2%, Llama 4 Maverick 17B Instruct 20.6%.

There are no published SWE-bench Verified results for Llama 4 Maverick 17B Instruct and Mistral Medium 3 yet, so there is no like-for-like coding score. On overall capability, Mistral Medium 3 leads, which tends to carry over to coding, but test on your own codebase. Both 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 Mistral Medium 3. Maximum output per response: Llama 4 Maverick 17B Instruct up to 16,384, Mistral Medium 3 up to 131,072 tokens.

Llama 4 Maverick 17B Instruct accepts text and images; Mistral Medium 3 accepts text and images. They handle the same number of input types.

Llama 4 Maverick 17B Instruct publishes its weights and can be self-hosted; Mistral Medium 3 is proprietary.

Mistral Medium 3 is the newest, released May 7, 2025. Llama 4 Maverick 17B Instruct came out Apr 5, 2025. Knowledge cutoff: Llama 4 Maverick 17B Instruct Aug 2024, Mistral Medium 3 May 2025.

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.