ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Mistral Large 4 vs Claude Sonnet 5.5 vs Inkling Small

Claude Sonnet 5.5 comes out ahead, 72 to 68 and 67 on our weighted score, though Inkling Small is 5× cheaper per token.

  1. Mistral AI

    Mistral Large 4

    Released Oct 6, 2026NewBeta

    67/100
    • ECI150.6
    • Price$0.70 / $2.10
    • Context1.05M
    Full specs Remove Mistral Large 4
  2. Our pick

    Anthropic

    Claude Sonnet 5.5

    Released Sep 28, 2026New

    72/100
    • ECI166.7
    • Price$2.00 / $10.00
    • Context1M
    Full specs Remove Claude Sonnet 5.5

  3. Thinking Machines

    Inkling Small

    Released Jul 30, 2026

    68/100
    • ECI150.5
    • Price$0.58 / $1.44
    • Context1.05M
    Full specs Remove Inkling Small
01 — Verdict

Claude Sonnet 5.5 is our pick

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%.

  • CapabilityClaude Sonnet 5.5Capabilities Index (ECI): Claude Sonnet 5.5 166.7 · Mistral Large 4 150.6 · Inkling Small 150.5
  • Lowest priceInkling SmallInkling Small $0.795 · Mistral Large 4 $1.05 · Claude Sonnet 5.5 $4.00 per 1M tokens (3:1 blend)
  • Longest contextMistral Large 4 and Inkling SmallMistral Large 4 1,048,576 · Inkling Small 1,048,576 · Claude Sonnet 5.5 1,000,000 tokens
  • Widest inputsClaude Sonnet 5.5 and Inkling SmallMistral Large 4: Text, Images · Claude Sonnet 5.5: Text, Images, PDFs · Inkling Small: Text, Images, Audio
  • Self-hostingInkling SmallPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightMistral Large 4Claude Sonnet 5.5Inkling Small
CapabilityCapabilities Index (ECI)50%779777
Price25%472052
Inputs & features15%708070
Context window10%616061
Overall100%67/10072/10068/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Mistral Large 4 vs Claude Sonnet 5.5 vs Inkling Small specifications side by side
SpecificationMistral Large 4Mistral AIClaude Sonnet 5.5AnthropicInkling SmallThinking Machines
Capability
Capabilities Index (ECI)150.6166.7 (best)150.5
ECI rank#57 of 165#5 of 165 (best)#58 of 165
GPQA DiamondGraduate-level science questions88.1%95.6% (best)88.5%
FrontierMath Tiers 1–3Research-level mathematics58.6%88.8% (best)46.3%
OTIS Mock AIME 2024–2025Competition mathematics98.3%100% (best)90.0%
SimpleQA VerifiedShort factual questions20.0%46.5% (best)19.1%
Price per million tokens
Input$0.70$2.00$0.58 (best)
Output$2.10$10.00$1.44 (best)
Cached input$0.07 (best)$0.10$0.116
Blended (3:1)$1.05$4.00$0.795 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Mistral APIOfficial Anthropic APIOfficial Thinking Machines API
Limits
Context window1,048,576 tokens (best)1,000,000 tokens1,048,576 tokens (best)
Max output262,144 tokens128,000 tokens1,048,576 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoYesNo
AudioNoNoYes
VideoNoNoNo
ReasoningYeslow · medium · highYeslow · medium · high · xhigh · maxYeslow · medium · high · xhigh · max
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsProprietaryProprietaryOpenApache-2.0
API model IDmistral-large-4claude-sonnet-5-5thinkingmachines/Inkling-Small
API providers1534 (best)12
ReleasedOct 6, 2026Sep 28, 2026Jul 30, 2026
Knowledge cutoff—Jun 2026—
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Mistral Large 4$11.20
  • Claude Sonnet 5.5$40.00
  • Inkling Small$8.68
04 — Questions

Which should you choose?

Which is better: Mistral Large 4, Claude Sonnet 5.5 or Inkling Small?

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%.

Which is cheaper, Mistral Large 4, Claude Sonnet 5.5 or Inkling Small?

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).

Which scores higher on benchmarks?

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%.

Which is better for coding?

There are no published SWE-bench Verified results for Mistral Large 4, Claude Sonnet 5.5 and Inkling Small 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.

Which has the bigger context window?

Mistral Large 4 and Inkling Small 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: Mistral Large 4 up to 262,144, Claude Sonnet 5.5 up to 128,000, Inkling Small up to 1,048,576 tokens.

Which can read images, PDFs, audio or video?

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

Are any of these open source?

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

Which is newer?

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.

How do you decide the winner?

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.

05 — Keep comparing

Related comparisons