ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Mistral Large 4 vs GPT-6 Astra vs Inkling Small

Too close to call on our weighted score (Inkling Small 68, GPT-6 Astra 68, Mistral Large 4 67). The right pick depends on what you value most.

  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. OpenAI

    GPT-6 Astra

    Released Sep 4, 2026New

    68/100
    • ECI169.1
    • Price$10.00 / $50.00
    • Context1.05M
    Full specs Remove GPT-6 Astra

  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

Too close to call

It is close. Our weighted score puts them within a point (Inkling Small 68/100, GPT-6 Astra 68/100, Mistral Large 4 67/100), so choose by what matters most for your work: GPT-6 Astra for raw capability and Inkling Small on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGPT-6 AstraCapabilities Index (ECI): GPT-6 Astra 169.1 · Mistral Large 4 150.6 · Inkling Small 150.5
  • Lowest priceInkling SmallInkling Small $0.795 · Mistral Large 4 $1.05 · GPT-6 Astra $20.00 per 1M tokens (3:1 blend)
  • Longest contextAbout the sameGPT-6 Astra 1,050,000 · Mistral Large 4 1,048,576 · Inkling Small 1,048,576 tokens
  • Widest inputsGPT-6 Astra and Inkling SmallMistral Large 4: Text, Images · GPT-6 Astra: Text, Images, PDFs · Inkling Small: Text, Images, Audio
  • Self-hostingInkling SmallPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightMistral Large 4GPT-6 AstraInkling Small
CapabilityCapabilities Index (ECI)50%7710077
Price25%47052
Inputs & features15%708070
Context window10%616161
Overall100%67/10068/10068/100
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 GPT-6 Astra vs Inkling Small specifications side by side
SpecificationMistral Large 4Mistral AIGPT-6 AstraOpenAIInkling SmallThinking Machines
Capability
Capabilities Index (ECI)150.6169.1 (best)150.5
ECI rank#57 of 165#1 of 165 (best)#58 of 165
GPQA DiamondGraduate-level science questions88.1%95.8% (best)88.5%
FrontierMath Tiers 1–3Research-level mathematics58.6%93.7% (best)46.3%
OTIS Mock AIME 2024–2025Competition mathematics98.3%100% (best)90.0%
SimpleQA VerifiedShort factual questions20.0%75.6% (best)19.1%
Price per million tokens
Input$0.70$10.00$0.58 (best)
Output$2.10$50.00$1.44 (best)
Cached input$0.07 (best)$1.00$0.116
Blended (3:1)$1.05$20.00$0.795 (best)
Long-context rateSame rateOver 272K: $20.00 / $75.00Same rate
Price sourceOfficial Mistral APIOfficial OpenAI APIOfficial Thinking Machines API
Limits
Context window1,048,576 tokens1,050,000 tokens (best)1,048,576 tokens
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-4gpt-6-astrathinkingmachines/Inkling-Small
API providers1537 (best)12
ReleasedOct 6, 2026Sep 4, 2026Jul 30, 2026
Knowledge cutoff—Apr 30, 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
  • GPT-6 Astra$200.00
  • Inkling Small$8.68
04 — Questions

Which should you choose?

Which is better: Mistral Large 4, GPT-6 Astra or Inkling Small?

It is close. Our weighted score puts them within a point (Inkling Small 68/100, GPT-6 Astra 68/100, Mistral Large 4 67/100), so choose by what matters most for your work: GPT-6 Astra for raw capability and Inkling Small on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Mistral Large 4, GPT-6 Astra 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); GPT-6 Astra costs $10.00 input / $50.00 output per million tokens (official OpenAI 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 $20.00 for GPT-6 Astra (25× as much).

Which scores higher on benchmarks?

GPT-6 Astra scores higher on the Capabilities Index (ECI): GPT-6 Astra 169.1 (#1 of 165), Mistral Large 4 150.6 (#57 of 165) and Inkling Small 150.5 (#58 of 165). Their confidence ranges do not overlap (165.9–174.3 vs 147.4–153.5), so the gap is a real one. On individual benchmarks: GPQA Diamond — GPT-6 Astra 95.8%, Inkling Small 88.5%, Mistral Large 4 88.1%; FrontierMath Tiers 1–3 — GPT-6 Astra 93.7%, Mistral Large 4 58.6%, Inkling Small 46.3%; OTIS Mock AIME 2024–2025 — GPT-6 Astra 100%, Mistral Large 4 98.3%, Inkling Small 90.0%; SimpleQA Verified — GPT-6 Astra 75.6%, 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, GPT-6 Astra and Inkling Small yet, so there is no like-for-like coding score. On overall capability, GPT-6 Astra 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?

Their context windows are effectively the same size: Mistral Large 4 1,048,576, GPT-6 Astra 1,050,000 and Inkling Small 1,048,576 tokens. Maximum output per response: Mistral Large 4 up to 262,144, GPT-6 Astra 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; GPT-6 Astra accepts text, images and PDFs; Inkling Small accepts text, images and audio. GPT-6 Astra 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 GPT-6 Astra is proprietary.

Which is newer?

Mistral Large 4 is the newest, released Oct 6, 2026. GPT-6 Astra came out Sep 4, 2026; Inkling Small came out Jul 30, 2026. Knowledge cutoff: GPT-6 Astra Apr 30, 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