Gemma 3 27B IT vs Mistral Small 3

Gemma 3 27B IT is the better all-round choice, scoring 49/100 against Mistral Small 3 (39). It leads on capability, inputs & features and context window. Mistral Small 3 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 and OTIS Mock AIME 2024–2025), because Mistral Small 3 has no Capabilities Index score yet.

Mistral Small 3 is cheaper at $0.05 input / $0.08 output per million tokens (median across 6 API providers). Gemma 3 27B IT costs $0.11 input / $0.30 output per million tokens (median across 16 API providers). At a typical mix of three input tokens to one output token, that is $0.058 per million tokens for Mistral Small 3 versus $0.157 for Gemma 3 27B IT (2.7× as much).

Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025): Gemma 3 27B IT 35.1% and Mistral Small 3 27.0%. On individual benchmarks: GPQA Diamond — Gemma 3 27B IT 47.7%, Mistral Small 3 47.3%; OTIS Mock AIME 2024–2025 — Gemma 3 27B IT 22.5%, Mistral Small 3 6.7%.

There are no published SWE-bench Verified results for Gemma 3 27B IT and Mistral Small 3 yet, so there is no like-for-like coding score. On overall capability, Gemma 3 27B IT leads, which tends to carry over to coding, but test on your own codebase. Note that Mistral Small 3 does not support tool calling, which most coding agents need.

Gemma 3 27B IT has the largest context window at 131,072 tokens, against 32,768 for Mistral Small 3. Maximum output per response: Gemma 3 27B IT up to 131,072, Mistral Small 3 up to 16,384 tokens.

Gemma 3 27B IT accepts text and images; Mistral Small 3 accepts text. Gemma 3 27B IT handles the widest range of inputs.

Yes, both publish their weights, so you can self-host them.

Gemma 3 27B IT is the newest, released Mar 12, 2025. Mistral Small 3 came out Jan 30, 2025. Knowledge cutoff: Gemma 3 27B IT Aug 2024, Mistral Small 3 Oct 31, 2023.

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 Nov 2, 2026.