ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Step 5 Preview vs Claude Fable 5.2 vs Pareto 26.10

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

Price in rating: Included · Exclude price

  1. StepFun

    Step 5 Preview

    Released Sep 16, 2026

    57/100
    • ECI—
    • Price$1.00 / $2.70
    • Context1M
  2. Anthropic

    Claude Fable 5.2

    Released Nov 9, 2026New

    37/100
    • ECI173.5
    • Price$8.00 / $40.00
    • Context1M
  3. Unbiased

    Pareto 26.10

    Released Oct 15, 2026New

    49/100
    • ECI—
    • Price$0.80 / $3.20
    • Context1.05M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Step 5 Preview 57/100, Pareto 26.10 49/100, Claude Fable 5.2 37/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. 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 pricePareto 26.10Pareto 26.10 $1.40 · Step 5 Preview $1.43 · Claude Fable 5.2 $16.00 per 1M tokens (3:1 blend)
  • Longest contextPareto 26.10Pareto 26.10 1,048,576 · Step 5 Preview 1,000,000 · Claude Fable 5.2 1,000,000 tokens
  • Widest inputsStep 5 Preview and Claude Fable 5.2Step 5 Preview: Text, Images, Video · Claude Fable 5.2: Text, Images, PDFs · Pareto 26.10: Text, Images
  • Self-hostingStep 5 PreviewPublishes downloadable weights
How the score is built
MeasureWeightStep 5 PreviewClaude Fable 5.2Pareto 26.10
Price50%41041
Inputs & features30%808050
Context window20%646465
Specs & price only100%57/10037/10049/100

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.

Step 5 Preview vs Claude Fable 5.2 vs Pareto 26.10 specifications side by side
SpecificationStep 5 PreviewStepFunClaude Fable 5.2AnthropicPareto 26.10Unbiased
Capability
Capabilities Index (ECI)—173.5—
ECI rank—#2 of 158—
GPQA DiamondGraduate-level science questions—96.0%—
FrontierMath Tiers 1–3Research-level mathematics—95.1%—
OTIS Mock AIME 2024–2025Competition mathematics—99.7%—
SimpleQA VerifiedShort factual questions—94.0%—
Price per million tokens
Input$1.00$8.00$0.80 (best)
Output$2.70 (best)$40.00$3.20
Cached input$0.10 (best)$0.20—
Blended (3:1)$1.43$16.00$1.40 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial StepFun (Global) APIOfficial Anthropic APIMedian of 2 providers
Limits
Context window1,000,000 tokens1,000,000 tokens1,048,576 tokens (best)
Max output1,000,000 tokens (best)128,000 tokens131,072 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoYesNo
AudioNoNoNo
VideoYesNoNo
ReasoningYeslow · medium · highYeslow · medium · high · xhigh · maxNo
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsOpenProprietaryProprietary
API model IDstep-5-previewclaude-fable-5-2—
API providers2125 (best)2
ReleasedSep 16, 2026Nov 9, 2026Oct 15, 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.

  • Step 5 Preview$15.40
  • Claude Fable 5.2$160.00
  • Pareto 26.10$14.40
04 — Questions

Which should you choose?

Which is better: Step 5 Preview, Claude Fable 5.2 or Pareto 26.10?

There is not enough shared capability evidence to name an overall winner. The scores (Step 5 Preview 57/100, Pareto 26.10 49/100, Claude Fable 5.2 37/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Step 5 Preview, Claude Fable 5.2 or Pareto 26.10?

Pareto 26.10 is cheaper at $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); Claude Fable 5.2 costs $8.00 input / $40.00 output per million tokens (official Anthropic API price). At a typical mix of three input tokens to one output token, that is $1.40 per million tokens for Pareto 26.10 versus $1.43 for Step 5 Preview (1× as much) and $16.00 for Claude Fable 5.2 (11× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Step 5 Preview has not been scored yet, Claude Fable 5.2 has an ECI of 173.5 and Pareto 26.10 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Step 5 Preview, Claude Fable 5.2 and Pareto 26.10 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?

Pareto 26.10 has the largest context window at 1,048,576 tokens, against 1,000,000 for Step 5 Preview and 1,000,000 for Claude Fable 5.2. Maximum output per response: Step 5 Preview up to 1,000,000, Claude Fable 5.2 up to 128,000, Pareto 26.10 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Step 5 Preview accepts text, images and video; Claude Fable 5.2 accepts text, images and PDFs; Pareto 26.10 accepts text and images. Step 5 Preview handles the widest range of inputs.

Are any of these open source?

Step 5 Preview publishes its weights and can be self-hosted; Claude Fable 5.2 and Pareto 26.10 is proprietary.

Which is newer?

Claude Fable 5.2 is the newest, released Nov 9, 2026. Pareto 26.10 came out Oct 15, 2026; Step 5 Preview came out Sep 16, 2026. Knowledge cutoff: Claude Fable 5.2 Jun 2026.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.