ZMIME
Comparison · 2 models · Updated Nov 19, 2026

Dhīr 5B MoE vs DaisyRose-27B

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

Price in rating: Included · Exclude price

  1. ZenteiQ

    Dhīr 5B MoE

    Released Nov 3, 2026New

    0/100
    • ECI—
    • Price—
    • Context16K
  2. RadixArk

    DaisyRose-27B

    Released Nov 18, 2026New

    43/100
    • ECI—
    • Price—
    • Context262K
  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (DaisyRose-27B 43/100, Dhīr 5B MoE 0/100) 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
  • Longest contextDaisyRose-27BDaisyRose-27B 262,144 · Dhīr 5B MoE 16,384 tokens
  • Widest inputsDaisyRose-27BDhīr 5B MoE: Text · DaisyRose-27B: Text, Images
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightDhīr 5B MoEDaisyRose-27B
Context window100%043
Specs & price only100%0/10043/100

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.

Dhīr 5B MoE vs DaisyRose-27B specifications side by side
SpecificationDhīr 5B MoEZenteiQDaisyRose-27BRadixArk
TaskMultilingual assistantAgentic coding
Published capabilitiesMixture-of-experts assistant supporting English and ten Indian languages for offline deployment.Post-trained from Qwen3.8-27B on 1,200 agent tasks. RadixArk reports 12% pass@1 on Terminal-Bench 4.1.
Model size5.09B total / 1.79B active27B parameters
AccessOpen weights for on-premises or offline usePublic BF16, FP8 and NVFP4 checkpoints
SourcesPublisher documentation · Additional documentationPublisher documentation
Capability
Capabilities Index (ECI)——
ECI rank——
Price per million tokens
Input——
Output——
Cached input——
Blended (3:1)——
Long-context rate——
Price source——
Limits
Context window16,384 tokens262,144 tokens (best)
Max output——
Inputs and features
TextYesYes
ImagesNoYes
PDFsNoNo
AudioNoNo
VideoNoNo
ReasoningUnconfirmedUnconfirmed
Tool calling——
Structured output——
Availability
WeightsOpenOpenApache-2.0
API model ID——
API providers——
ReleasedNov 3, 2026Nov 18, 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.

  • Dhīr 5B MoE—
  • DaisyRose-27B—
04 — Questions

Which should you choose?

Which is better: Dhīr 5B MoE or DaisyRose-27B?

There is not enough shared capability evidence to name an overall winner. The scores (DaisyRose-27B 43/100, Dhīr 5B MoE 0/100) 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, Dhīr 5B MoE or DaisyRose-27B?

None of these models has a published per-token price.

Which scores higher on benchmarks?

There is no independent benchmark that covers both models yet. Dhīr 5B MoE has not been scored yet and DaisyRose-27B has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Dhīr 5B MoE and DaisyRose-27B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Dhīr 5B MoE and DaisyRose-27B has no confirmed tool-calling support in this comparison.

Which has the bigger context window?

DaisyRose-27B has the largest context window at 262,144 tokens, against 16,384 for Dhīr 5B MoE.

Which can read images, PDFs, audio or video?

Dhīr 5B MoE accepts text; DaisyRose-27B accepts text and images. DaisyRose-27B handles the widest range of inputs.

Are any of these open source?

Yes, both publish their weights (Apache-2.0), so you can self-host them.

Which is newer?

DaisyRose-27B is the newest, released Nov 18, 2026. Dhīr 5B MoE came out Nov 3, 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.