ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Pareto vs Claude Sonnet 5.5 vs Fugu Max

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. Unbiased

    Pareto

    Released Sep 17, 2026

    34/100
    • ECI—
    • Price$2.50 / $7.50
    • Context262K
  2. Anthropic

    Claude Sonnet 5.5

    Released Sep 28, 2026New

    47/100
    • ECI166.6
    • Price$2.00 / $10.00
    • Context1M
  3. Sakana AI

    Fugu Max

    Released Sep 11, 2026

    47/100
    • ECI—
    • Price$2.00 / $6.00
    • Context1M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Claude Sonnet 5.5 47/100, Fugu Max 47/100, Pareto 34/100) 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 priceFugu MaxFugu Max $3.00 · Pareto $3.75 · Claude Sonnet 5.5 $4.00 per 1M tokens (3:1 blend)
  • Longest contextClaude Sonnet 5.5 and Fugu MaxClaude Sonnet 5.5 1,000,000 · Fugu Max 1,000,000 · Pareto 262,144 tokens
  • Widest inputsClaude Sonnet 5.5 and Fugu MaxPareto: Text, Images · Claude Sonnet 5.5: Text, Images, PDFs · Fugu Max: Text, Images, PDFs
  • Self-hostingNo confirmed open weightsAll three are available only through APIs
How the score is built
MeasureWeightParetoClaude Sonnet 5.5Fugu Max
Price50%222026
Inputs & features30%508070
Context window20%436464
Specs & price only100%34/10047/10047/100

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.

Pareto vs Claude Sonnet 5.5 vs Fugu Max specifications side by side
SpecificationParetoUnbiasedClaude Sonnet 5.5AnthropicFugu MaxSakana AI
Capability
Capabilities Index (ECI)—166.6—
ECI rank—#9 of 158—
GPQA DiamondGraduate-level science questions—95.6%—
FrontierMath Tiers 1–3Research-level mathematics—88.8%—
OTIS Mock AIME 2024–2025Competition mathematics—100%—
SimpleQA VerifiedShort factual questions—46.5%—
Price per million tokens
Input$2.50$2.00 (best)$2.00 (best)
Output$7.50$10.00$6.00 (best)
Cached input—$0.10—
Blended (3:1)$3.75$4.00$3.00 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 3 providersOfficial Anthropic APIMedian of 9 providers
Limits
Context window262,144 tokens1,000,000 tokens (best)1,000,000 tokens (best)
Max output131,072 tokens (best)128,000 tokens128,000 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoYesYes
AudioNoNoNo
VideoNoNoNo
ReasoningNoYeslow · medium · high · xhigh · maxYes
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsProprietaryProprietaryProprietary
API model ID—claude-sonnet-5-5—
API providers357 (best)9
ReleasedSep 17, 2026Sep 28, 2026Sep 11, 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.

  • Pareto$40.00
  • Claude Sonnet 5.5$40.00
  • Fugu Max$32.00
04 — Questions

Which should you choose?

Which is better: Pareto, Claude Sonnet 5.5 or Fugu Max?

There is not enough shared capability evidence to name an overall winner. The scores (Claude Sonnet 5.5 47/100, Fugu Max 47/100, Pareto 34/100) 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, Pareto, Claude Sonnet 5.5 or Fugu Max?

Fugu Max is cheaper at $2.00 input / $6.00 output per million tokens (median across 9 API providers). Pareto costs $2.50 input / $7.50 output per million tokens (median across 3 API providers); 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 $3.00 per million tokens for Fugu Max versus $3.75 for Pareto (1.3× as much) and $4.00 for Claude Sonnet 5.5 (1.3× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Pareto has not been scored yet, Claude Sonnet 5.5 has an ECI of 166.6 and Fugu Max has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Pareto, Claude Sonnet 5.5 and Fugu Max 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?

Claude Sonnet 5.5 and Fugu Max have the largest context windows (1,000,000 and 1,000,000 tokens), against 262,144 for Pareto. Maximum output per response: Pareto up to 131,072, Claude Sonnet 5.5 up to 128,000, Fugu Max up to 128,000 tokens.

Which can read images, PDFs, audio or video?

Pareto accepts text and images; Claude Sonnet 5.5 accepts text, images and PDFs; Fugu Max accepts text, images and PDFs. Claude Sonnet 5.5 handles the widest range of inputs.

Are any of these open source?

No. Pareto, Claude Sonnet 5.5 and Fugu Max are proprietary and only available through APIs and apps.

Which is newer?

Claude Sonnet 5.5 is the newest, released Sep 28, 2026. Pareto came out Sep 17, 2026; Fugu Max came out Sep 11, 2026. Knowledge cutoff: Claude Sonnet 5.5 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.