ZMIME
Comparison · 3 models · Updated Nov 19, 2026

Pareto 26.10 vs Ripple-65B Preview vs Step 5 Preview

No independent capability benchmark covers every model here yet. The score uses context window.

Price in rating: Excluded · Include price

  1. Unbiased

    Pareto 26.10

    Released Oct 15, 2026New

    65/100
    • ECI—
    • Price$0.80 / $3.20
    • Context1.05M
  2. Ricursive Intelligence

    Ripple-65B Preview

    Released Nov 4, 2026New

    65/100
    • ECI—
    • Price—
    • Context1.05M
  3. StepFun

    Step 5 Preview

    Released Sep 16, 2026

    64/100
    • 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 (Pareto 26.10 65/100, Ripple-65B Preview 65/100, Step 5 Preview 64/100) compare the available specifications only. The score weighs context window 100%. 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 per 1M tokens (3:1 blend) · Ripple-65B Preview unpriced
  • Longest contextPareto 26.10 and Ripple-65B PreviewPareto 26.10 1,048,576 · Ripple-65B Preview 1,048,576 · Step 5 Preview 1,000,000 tokens
  • Widest inputsStep 5 PreviewPareto 26.10: Text, Images · Ripple-65B Preview: Text · Step 5 Preview: Text, Images, Video
  • Self-hostingRipple-65B Preview and Step 5 PreviewPublishes downloadable weights
How the score is built
MeasureWeightPareto 26.10Ripple-65B PreviewStep 5 Preview
Context window100%656564
Specs only100%65/10065/10064/100

Left out because at least one model lacks the data: capability and inputs & features. 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.

Pareto 26.10 vs Ripple-65B Preview vs Step 5 Preview specifications side by side
SpecificationPareto 26.10UnbiasedRipple-65B PreviewRicursive IntelligenceStep 5 PreviewStepFun
Task—Language generation and coding—
Published capabilitiesBlended multimodal model that selects frontier and open models for each request and blends their outputs into one answerDense transformer trained on 12 trillion tokens with a focus on long-context software engineering.StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window
Model size—65B parameters—
Access—Public weights and hosted inference via Together AI, OpenRouter and Fireworks—
Sources—Publisher documentation · Model weights—
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.80 (best)—$1.00
Output$3.20—$2.70 (best)
Cached input——$0.10
Blended (3:1)$1.40 (best)—$1.43
Long-context rateSame rate—Same rate
Price sourceMedian of 2 providers—Official StepFun (Global) API
Limits
Context window1,048,576 tokens (best)1,048,576 tokens (best)1,000,000 tokens
Max output131,072 tokens—1,000,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoYes
ReasoningNoUnconfirmedYeslow · medium · high
Tool callingYes—Yes
Structured outputNo—Yes
Availability
WeightsProprietaryOpenOpen
API model ID——step-5-preview
API providers2—21 (best)
ReleasedOct 15, 2026Nov 4, 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.

  • Pareto 26.10$14.40
  • Ripple-65B Preview—
  • Step 5 Preview$15.40
04 — Questions

Which should you choose?

Which is better: Pareto 26.10, Ripple-65B Preview or Step 5 Preview?

There is not enough shared capability evidence to name an overall winner. The scores (Pareto 26.10 65/100, Ripple-65B Preview 65/100, Step 5 Preview 64/100) compare the available specifications only. The score weighs context window 100%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Pareto 26.10, Ripple-65B Preview or Step 5 Preview?

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). 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). Ripple-65B Preview has no published per-token price.

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Pareto 26.10 has not been scored yet, Ripple-65B Preview 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 Pareto 26.10, Ripple-65B Preview and Step 5 Preview yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Ripple-65B Preview has no confirmed tool-calling support in this comparison.

Which has the bigger context window?

Pareto 26.10 and Ripple-65B Preview 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: Pareto 26.10 up to 131,072, Step 5 Preview up to 1,000,000 tokens.

Which can read images, PDFs, audio or video?

Pareto 26.10 accepts text and images; Ripple-65B Preview accepts text; Step 5 Preview accepts text, images and video. Step 5 Preview handles the widest range of inputs.

Are any of these open source?

Ripple-65B Preview and Step 5 Preview publishes its weights and can be self-hosted; Pareto 26.10 is proprietary.

Which is newer?

Ripple-65B Preview is the newest, released Nov 4, 2026. Pareto 26.10 came out Oct 15, 2026; Step 5 Preview came out Sep 16, 2026.

How do you decide the winner?

This rating uses context window (100%, 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 19, 2026.