ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Fugu Ultra v2 vs Muse Wonder Full vs Claude Opus 4.5

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

Price in rating: Excluded · Include price

  1. Sakana AI

    Fugu Ultra v2

    Released Sep 11, 2026

    68/100
    • ECI—
    • Price$5.00 / $30.00
    • Context1M
  2. Meta

    Muse Wonder Full

    Released Oct 12, 2026New

    74/100
    • ECI—
    • Price$4.80 / $24.00
    • Context1.05M
  3. Anthropic

    Claude Opus 4.5

    Released Nov 24, 2025

    64/100
    • ECI151.9
    • Price$5.00 / $25.00
    • Context200K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Muse Wonder Full 74/100, Fugu Ultra v2 68/100, Claude Opus 4.5 64/100) 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 priceMuse Wonder FullMuse Wonder Full $9.60 · Claude Opus 4.5 $10.00 · Fugu Ultra v2 $11.25 per 1M tokens (3:1 blend)
  • Longest contextMuse Wonder FullMuse Wonder Full 1,048,576 · Fugu Ultra v2 1,000,000 · Claude Opus 4.5 200,000 tokens
  • Widest inputsMuse Wonder FullFugu Ultra v2: Text, Images, PDFs · Muse Wonder Full: Text, Images, Audio, Video · Claude Opus 4.5: Text, Images, PDFs
  • Self-hostingNo confirmed open weightsAll three are available only through APIs
How the score is built
MeasureWeightFugu Ultra v2Muse Wonder FullClaude Opus 4.5
Inputs & features60%708080
Context window40%646539
Specs only100%68/10074/10064/100

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.

Fugu Ultra v2 vs Muse Wonder Full vs Claude Opus 4.5 specifications side by side
SpecificationFugu Ultra v2Sakana AIMuse Wonder FullMetaClaude Opus 4.5Anthropic
Capability
Capabilities Index (ECI)——151.9
ECI rank——#60 of 158
GPQA DiamondGraduate-level science questions——86.1%
FrontierMath Tiers 1–3Research-level mathematics——34.4%
OTIS Mock AIME 2024–2025Competition mathematics——86.1%
SWE-bench VerifiedFixing real GitHub issues——76.7%
SimpleQA VerifiedShort factual questions——45.7%
Price per million tokens
Input$5.00$4.80 (best)$5.00
Output$30.00$24.00 (best)$25.00
Cached input——$0.50
Blended (3:1)$11.25$9.60 (best)$10.00
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 6 providersMedian of 1 providersOfficial Anthropic API
Limits
Context window1,000,000 tokens1,048,576 tokens (best)200,000 tokens
Max output128,000 tokens (best)—64,000 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsYesNoYes
AudioNoYesNo
VideoNoYesNo
ReasoningYesYesYeslow · medium · high
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsProprietaryProprietaryProprietary
API model ID——claude-opus-4-5
API providers6140 (best)
ReleasedSep 11, 2026Oct 12, 2026Nov 24, 2025
Knowledge cutoffAug 28, 2026—May 2025
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.

  • Fugu Ultra v2$110.00
  • Muse Wonder Full$96.00
  • Claude Opus 4.5$100.00
04 — Questions

Which should you choose?

Which is better: Fugu Ultra v2, Muse Wonder Full or Claude Opus 4.5?

There is not enough shared capability evidence to name an overall winner. The scores (Muse Wonder Full 74/100, Fugu Ultra v2 68/100, Claude Opus 4.5 64/100) 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, Fugu Ultra v2, Muse Wonder Full or Claude Opus 4.5?

Muse Wonder Full is cheaper at $4.80 input / $24.00 output per million tokens (median across 1 API provider). Claude Opus 4.5 costs $5.00 input / $25.00 output per million tokens (official Anthropic API price); Fugu Ultra v2 costs $5.00 input / $30.00 output per million tokens (median across 6 API providers). At a typical mix of three input tokens to one output token, that is $9.60 per million tokens for Muse Wonder Full versus $10.00 for Claude Opus 4.5 (1× as much) and $11.25 for Fugu Ultra v2 (1.2× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Fugu Ultra v2 has not been scored yet, Muse Wonder Full has not been scored yet and Claude Opus 4.5 has an ECI of 151.9.

Which is better for coding?

There are no published SWE-bench Verified results for Fugu Ultra v2 and Muse Wonder Full 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?

Muse Wonder Full has the largest context window at 1,048,576 tokens, against 1,000,000 for Fugu Ultra v2 and 200,000 for Claude Opus 4.5. Maximum output per response: Fugu Ultra v2 up to 128,000, Claude Opus 4.5 up to 64,000 tokens.

Which can read images, PDFs, audio or video?

Fugu Ultra v2 accepts text, images and PDFs; Muse Wonder Full accepts text, images, audio and video; Claude Opus 4.5 accepts text, images and PDFs. Muse Wonder Full handles the widest range of inputs.

Are any of these open source?

No. Fugu Ultra v2, Muse Wonder Full and Claude Opus 4.5 are proprietary and only available through APIs and apps.

Which is newer?

Muse Wonder Full is the newest, released Oct 12, 2026. Fugu Ultra v2 came out Sep 11, 2026; Claude Opus 4.5 came out Nov 24, 2025. Knowledge cutoff: Fugu Ultra v2 Aug 28, 2026, Claude Opus 4.5 May 2025.

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.