Inkling Small vs Mistral Large 4 vs Claude Sonnet 5.5

Claude Sonnet 5.5 is the better all-round choice, scoring 72/100 against Inkling Small (68) and Mistral Large 4 (67). It leads on capability and inputs & features. Inkling Small wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Inkling Small is cheaper at $0.58 input / $1.44 output per million tokens (official Thinking Machines API price). Mistral Large 4 costs $0.70 input / $2.10 output per million tokens (official Mistral API price); Claude Sonnet 5.5 costs $2.00 input / $10.00 output per million tokens (official Anthropic API price). At a typical mix of three input tokens to one output token, that is $0.795 per million tokens for Inkling Small versus $1.05 for Mistral Large 4 (1.3× as much) and $4.00 for Claude Sonnet 5.5 (5× as much).

Claude Sonnet 5.5 scores higher on the Capabilities Index (ECI): Claude Sonnet 5.5 166.7 (#5 of 165), Mistral Large 4 150.6 (#57 of 165) and Inkling Small 150.5 (#58 of 165). Their confidence ranges do not overlap (163.6–171.3 vs 147.4–153.5), so the gap is a real one. On individual benchmarks: GPQA Diamond — Claude Sonnet 5.5 95.6%, Inkling Small 88.5%, Mistral Large 4 88.1%; FrontierMath Tiers 1–3 — Claude Sonnet 5.5 88.8%, Mistral Large 4 58.6%, Inkling Small 46.3%; OTIS Mock AIME 2024–2025 — Claude Sonnet 5.5 100%, Mistral Large 4 98.3%, Inkling Small 90.0%; SimpleQA Verified — Claude Sonnet 5.5 46.5%, Mistral Large 4 20.0%, Inkling Small 19.1%.

There are no published SWE-bench Verified results for Inkling Small, Mistral Large 4 and Claude Sonnet 5.5 yet, so there is no like-for-like coding score. On overall capability, Claude Sonnet 5.5 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.

Inkling Small and Mistral Large 4 have the largest context windows (1,048,576 and 1,048,576 tokens), against 1,000,000 for Claude Sonnet 5.5. Maximum output per response: Inkling Small up to 1,048,576, Mistral Large 4 up to 262,144, Claude Sonnet 5.5 up to 128,000 tokens.

Inkling Small accepts text, images and audio; Mistral Large 4 accepts text and images; Claude Sonnet 5.5 accepts text, images and PDFs. Inkling Small handles the widest range of inputs.

Inkling Small publishes its weights (Apache-2.0) and can be self-hosted; Mistral Large 4 and Claude Sonnet 5.5 is proprietary.

Mistral Large 4 is the newest, released Oct 6, 2026. Claude Sonnet 5.5 came out Sep 28, 2026; Inkling Small came out Jul 30, 2026. Knowledge cutoff: Claude Sonnet 5.5 Jun 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.