Inkling vs Mistral Large 4

Mistral Large 4 is the better all-round choice, scoring 67/100 against Inkling (63). It leads on capability and price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Mistral Large 4 is cheaper at $0.70 input / $2.10 output per million tokens (official Mistral API price). Inkling costs $1.00 input / $4.05 output per million tokens (official Thinking Machines API price). At a typical mix of three input tokens to one output token, that is $1.05 per million tokens for Mistral Large 4 versus $1.76 for Inkling (1.7× as much).

Mistral Large 4 scores higher on the Capabilities Index (ECI): Mistral Large 4 150.6 (#57 of 165) and Inkling 148.5 (#67 of 165). The confidence ranges of the top two overlap (147.4–153.5 vs 145.8–150.4), so treat the gap as small. On individual benchmarks: GPQA Diamond — Inkling 88.3%, Mistral Large 4 88.1%; FrontierMath Tiers 1–3 — Mistral Large 4 58.6%, Inkling 33.3%; OTIS Mock AIME 2024–2025 — Mistral Large 4 98.3%, Inkling 88.9%; SimpleQA Verified — Inkling 40.3%, Mistral Large 4 20.0%.

There are no published SWE-bench Verified results for Inkling and Mistral Large 4 yet, so there is no like-for-like coding score. On overall capability, Mistral Large 4 leads, which tends to carry over to coding, but test on your own codebase. Both support tool calling for agent workflows.

Inkling and Mistral Large 4 share the same 1,048,576-token context window. Maximum output per response: Inkling up to 1,048,576, Mistral Large 4 up to 262,144 tokens.

Inkling accepts text, images and audio; Mistral Large 4 accepts text and images. Inkling handles the widest range of inputs.

Inkling publishes its weights (Apache-2.0) and can be self-hosted; Mistral Large 4 is proprietary.

Mistral Large 4 is the newest, released Oct 6, 2026. Inkling came out Jul 15, 2026.

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.