ZMIME
Comparison · 3 models · Updated Nov 18, 2026

LongCat-2.0 vs LongCat-2.5-Preview vs Macaron V1 Tall

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

Price in rating: Excluded · Include price

  1. Meituan (LongCat)

    LongCat-2.0

    Released Jun 30, 2026

    47/100
    • ECI—
    • Price$0.30 / $1.20
    • Context1M
  2. Meituan (LongCat)

    LongCat-2.5-Preview

    Released Sep 25, 2026New

    62/100
    • ECI—
    • Price$0.30 / $1.20
    • Context1M
  3. Mindlab

    Macaron V1 Tall

    Released Jul 21, 2026

    53/100
    • ECI—
    • Price$0.247 / $1.43
    • Context262K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (LongCat-2.5-Preview 62/100, Macaron V1 Tall 53/100, LongCat-2.0 47/100) 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 priceLongCat-2.0 and LongCat-2.5-PreviewLongCat-2.0 $0.525 · LongCat-2.5-Preview $0.525 · Macaron V1 Tall $0.543 per 1M tokens (3:1 blend)
  • Longest contextLongCat-2.0 and LongCat-2.5-PreviewLongCat-2.0 1,000,000 · LongCat-2.5-Preview 1,000,000 · Macaron V1 Tall 262,144 tokens
  • Widest inputsLongCat-2.5-Preview and Macaron V1 TallLongCat-2.0: Text · LongCat-2.5-Preview: Text, Images · Macaron V1 Tall: Text, Images
  • Self-hostingLongCat-2.0 and Macaron V1 TallPublishes downloadable weights (MIT)
How the score is built
MeasureWeightLongCat-2.0LongCat-2.5-PreviewMacaron V1 Tall
Inputs & features60%356060
Context window40%646443
Specs only100%47/10062/10053/100

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.

LongCat-2.0 vs LongCat-2.5-Preview vs Macaron V1 Tall specifications side by side
SpecificationLongCat-2.0Meituan (LongCat)LongCat-2.5-PreviewMeituan (LongCat)Macaron V1 TallMindlab
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.30$0.30$0.247 (best)
Output$1.20 (best)$1.20 (best)$1.43
Cached input$0.006$0.006—
Blended (3:1)$0.525 (best)$0.525 (best)$0.543
Long-context rateSame rateSame rateSame rate
Price sourceOfficial LongCat APIOfficial LongCat APIMedian of 1 providers
Limits
Context window1,000,000 tokens (best)1,000,000 tokens (best)262,144 tokens
Max output131,072 tokens (best)131,072 tokens (best)32,768 tokens
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenProprietaryOpenMIT
API model IDLongCat-2.0LongCat-2.5-Preview—
API providers8 (best)31
ReleasedJun 30, 2026Sep 25, 2026Jul 21, 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.

  • LongCat-2.0$5.40
  • LongCat-2.5-Preview$5.40
  • Macaron V1 Tall$5.33
04 — Questions

Which should you choose?

Which is better: LongCat-2.0, LongCat-2.5-Preview or Macaron V1 Tall?

There is not enough shared capability evidence to name an overall winner. The scores (LongCat-2.5-Preview 62/100, Macaron V1 Tall 53/100, LongCat-2.0 47/100) 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, LongCat-2.0, LongCat-2.5-Preview or Macaron V1 Tall?

LongCat-2.0 is cheaper at $0.30 input / $1.20 output per million tokens (official LongCat API price). LongCat-2.5-Preview costs $0.30 input / $1.20 output per million tokens (official LongCat API price); Macaron V1 Tall costs $0.247 input / $1.43 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.525 per million tokens for LongCat-2.0 versus $0.525 for LongCat-2.5-Preview (1× as much) and $0.543 for Macaron V1 Tall (1× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. LongCat-2.0 has not been scored yet, LongCat-2.5-Preview has not been scored yet and Macaron V1 Tall has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for LongCat-2.0, LongCat-2.5-Preview and Macaron V1 Tall 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?

LongCat-2.0 and LongCat-2.5-Preview have the largest context windows (1,000,000 and 1,000,000 tokens), against 262,144 for Macaron V1 Tall. Maximum output per response: LongCat-2.0 up to 131,072, LongCat-2.5-Preview up to 131,072, Macaron V1 Tall up to 32,768 tokens.

Which can read images, PDFs, audio or video?

LongCat-2.0 accepts text; LongCat-2.5-Preview accepts text and images; Macaron V1 Tall accepts text and images. LongCat-2.5-Preview handles the widest range of inputs.

Are any of these open source?

LongCat-2.0 and Macaron V1 Tall publishes its weights (MIT) and can be self-hosted; LongCat-2.5-Preview is proprietary.

Which is newer?

LongCat-2.5-Preview is the newest, released Sep 25, 2026. Macaron V1 Tall came out Jul 21, 2026; LongCat-2.0 came out Jun 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.