ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Inkling Small vs Pareto 26.10 vs Step 5 Preview

No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.

Price in rating: Excluded · Include price

  1. Thinking Machines

    Inkling Small

    Released Jul 30, 2026

    68/100
    • ECI150.8
    • Price$0.58 / $1.44
    • Context1.05M
  2. Unbiased

    Pareto 26.10

    Released Oct 15, 2026New

    56/100
    • ECI—
    • Price$0.80 / $3.20
    • Context1.05M
  3. StepFun

    Step 5 Preview

    Released Sep 16, 2026

    74/100
    • ECI—
    • Price$1.00 / $2.70
    • Context1M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Step 5 Preview 74/100, Inkling Small 68/100, Pareto 26.10 56/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceInkling SmallInkling Small $0.795 · Pareto 26.10 $1.40 · Step 5 Preview $1.43 per 1M tokens (3:1 blend)
  • Longest contextInkling Small and Pareto 26.10Inkling Small 1,048,576 · Pareto 26.10 1,048,576 · Step 5 Preview 1,000,000 tokens
  • Widest inputsInkling Small and Step 5 PreviewInkling Small: Text, Images, Audio · Pareto 26.10: Text, Images · Step 5 Preview: Text, Images, Video
  • Self-hostingInkling Small and Step 5 PreviewPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightInkling SmallPareto 26.10Step 5 Preview
Inputs & features60%705080
Context window40%656564
Specs only100%68/10056/10074/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

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

Inkling Small vs Pareto 26.10 vs Step 5 Preview specifications side by side
SpecificationInkling SmallThinking MachinesPareto 26.10UnbiasedStep 5 PreviewStepFun
Capability
Capabilities Index (ECI)150.8——
ECI rank#65 of 158——
GPQA DiamondGraduate-level science questions88.5%——
FrontierMath Tiers 1–3Research-level mathematics46.3%——
OTIS Mock AIME 2024–2025Competition mathematics90.0%——
SimpleQA VerifiedShort factual questions19.1%——
Price per million tokens
Input$0.58 (best)$0.80$1.00
Output$1.44 (best)$3.20$2.70
Cached input$0.116—$0.10 (best)
Blended (3:1)$0.795 (best)$1.40$1.43
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Thinking Machines APIMedian of 2 providersOfficial StepFun (Global) API
Limits
Context window1,048,576 tokens (best)1,048,576 tokens (best)1,000,000 tokens
Max output1,048,576 tokens (best)131,072 tokens1,000,000 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoNoNo
AudioYesNoNo
VideoNoNoYes
ReasoningYeslow · medium · high · xhigh · maxNoYeslow · medium · high
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsOpenApache-2.0ProprietaryOpen
API model IDthinkingmachines/Inkling-Small:peft:262144—step-5-preview
API providers12221 (best)
ReleasedJul 30, 2026Oct 15, 2026Sep 16, 2026
Knowledge cutoff———
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.

  • Inkling Small$8.68
  • Pareto 26.10$14.40
  • Step 5 Preview$15.40
04 — Questions

Which should you choose?

Which is better: Inkling Small, Pareto 26.10 or Step 5 Preview?

There is not enough shared capability evidence to name an overall winner. The scores (Step 5 Preview 74/100, Inkling Small 68/100, Pareto 26.10 56/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Inkling Small, Pareto 26.10 or Step 5 Preview?

Inkling Small is cheaper at $0.58 input / $1.44 output per million tokens (official Thinking Machines API price). Pareto 26.10 costs $0.80 input / $3.20 output per million tokens (median across 2 API providers); Step 5 Preview costs $1.00 input / $2.70 output per million tokens (official StepFun (Global) 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 $1.40 for Pareto 26.10 (1.8× as much) and $1.43 for Step 5 Preview (1.8× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Inkling Small has an ECI of 150.8, Pareto 26.10 has not been scored yet and Step 5 Preview has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Inkling Small, Pareto 26.10 and Step 5 Preview yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

Inkling Small and Pareto 26.10 have the largest context windows (1,048,576 and 1,048,576 tokens), against 1,000,000 for Step 5 Preview. Maximum output per response: Inkling Small up to 1,048,576, Pareto 26.10 up to 131,072, Step 5 Preview up to 1,000,000 tokens.

Which can read images, PDFs, audio or video?

Inkling Small accepts text, images and audio; Pareto 26.10 accepts text and images; Step 5 Preview accepts text, images and video. Inkling Small handles the widest range of inputs.

Are any of these open source?

Inkling Small and Step 5 Preview publishes its weights (Apache-2.0) and can be self-hosted; Pareto 26.10 is proprietary.

Which is newer?

Pareto 26.10 is the newest, released Oct 15, 2026. Step 5 Preview came out Sep 16, 2026; Inkling Small came out Jul 30, 2026.

How do you decide the winner?

This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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 18, 2026.