ZMIME
Comparison · 3 models · Updated Nov 19, 2026

MAI Code 2 vs DaisyRose-27B vs Hy4

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

Price in rating: Included · Exclude price

  1. Microsoft

    MAI Code 2

    Released Nov 17, 2026New

    65/100
    • ECI—
    • Price$0.50 / $2.50
    • Context1.05M
  2. RadixArk

    DaisyRose-27B

    Released Nov 18, 2026New

    43/100
    • ECI—
    • Price—
    • Context262K
  3. Tencent

    Hy4

    Released Nov 4, 2026New

    65/100
    • ECI—
    • Price$0.834 / $2.50
    • Context1.05M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (MAI Code 2 65/100, Hy4 65/100, DaisyRose-27B 43/100) compare the available specifications and price. 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 priceMAI Code 2MAI Code 2 $1.00 · Hy4 $1.25 per 1M tokens (3:1 blend) · DaisyRose-27B unpriced
  • Longest contextMAI Code 2 and Hy4MAI Code 2 1,050,000 · Hy4 1,048,576 · DaisyRose-27B 262,144 tokens
  • Widest inputsSame inputsMAI Code 2: Text, Images · DaisyRose-27B: Text, Images · Hy4: Text, Images
  • Self-hostingDaisyRose-27BPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightMAI Code 2DaisyRose-27BHy4
Context window100%654365
Specs & price only100%65/10043/10065/100

Left out because at least one model lacks the data: capability, price 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.

MAI Code 2 vs DaisyRose-27B vs Hy4 specifications side by side
SpecificationMAI Code 2MicrosoftDaisyRose-27BRadixArkHy4Tencent
TaskCodingAgentic coding—
Published capabilitiesMixture-of-experts coding model for long-running engineering tasks and multi-file changes.Post-trained from Qwen3.8-27B on 1,200 agent tasks. RadixArk reports 12% pass@1 on Terminal-Bench 4.1.A next-generation multimodal productivity model with significantly enhanced Agent and complex task execution capabilities.
Model size80B active parameters27B parameters—
AccessGitHub CopilotPublic BF16, FP8 and NVFP4 checkpoints—
Billing termsPromotional GitHub Copilot token rates until May 17, 2027.——
SourcesPublisher documentation · Additional documentation · Pricing documentationPublisher documentation—
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.50 (best)—$0.834
Output$2.50 (best)—$2.50
Cached input$0.025 (best)—$0.042
Blended (3:1)$1.00 (best)—$1.25
Long-context rateSame rate—Same rate
Price sourceOfficial GitHub Copilot API—Official Tencent TokenHub API
Limits
Context window1,050,000 tokens (best)262,144 tokens1,048,576 tokens
Max output128,000 tokens (best)—65,536 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesUnconfirmedYeshigh
Tool callingYes—Yes
Structured output——No
Availability
WeightsProprietaryOpenApache-2.0Proprietary
API model ID——hy4
API providers——12
ReleasedNov 17, 2026Nov 18, 2026Nov 4, 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.

  • MAI Code 2$10.00
  • DaisyRose-27B—
  • Hy4$13.34
04 — Questions

Which should you choose?

Which is better: MAI Code 2, DaisyRose-27B or Hy4?

There is not enough shared capability evidence to name an overall winner. The scores (MAI Code 2 65/100, Hy4 65/100, DaisyRose-27B 43/100) compare the available specifications and price. 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, MAI Code 2, DaisyRose-27B or Hy4?

MAI Code 2 is cheaper at $0.50 input / $2.50 output per million tokens (official GitHub Copilot API price). Hy4 costs $0.834 input / $2.50 output per million tokens (official Tencent TokenHub API price). At a typical mix of three input tokens to one output token, that is $1.00 per million tokens for MAI Code 2 versus $1.25 for Hy4 (1.3× as much). DaisyRose-27B has no published per-token price.

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. MAI Code 2 has not been scored yet, DaisyRose-27B has not been scored yet and Hy4 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for MAI Code 2, DaisyRose-27B and Hy4 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that DaisyRose-27B has no confirmed tool-calling support in this comparison.

Which has the bigger context window?

MAI Code 2 and Hy4 have the largest context windows (1,050,000 and 1,048,576 tokens), against 262,144 for DaisyRose-27B. Maximum output per response: MAI Code 2 up to 128,000, Hy4 up to 65,536 tokens.

Which can read images, PDFs, audio or video?

MAI Code 2 accepts text and images; DaisyRose-27B accepts text and images; Hy4 accepts text and images. They handle the same number of input types.

Are any of these open source?

DaisyRose-27B publishes its weights (Apache-2.0) and can be self-hosted; MAI Code 2 and Hy4 is proprietary.

Which is newer?

DaisyRose-27B is the newest, released Nov 18, 2026. MAI Code 2 came out Nov 17, 2026; Hy4 came out Nov 4, 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.