ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Ornith 1.0 35B vs Laguna XS 2.1 vs Seed Character

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

Price in rating: Included · Exclude price

  1. DeepReinforce

    Ornith 1.0 35B

    Released Jun 25, 2026

    53/100
    • ECI—
    • Price—
    • Context262K
  2. Poolside

    Laguna XS 2.1

    Released Jul 2, 2026

    38/100
    • ECI—
    • PriceFree / Free
    • Context262K
  3. ByteDance Seed

    Seed Character

    Released Jun 23, 2026

    65/100
    • ECI—
    • Price$0.119 / $0.297
    • Context256K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Seed Character 65/100, Ornith 1.0 35B 53/100, Laguna XS 2.1 38/100) compare the available specifications and price. 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 priceLaguna XS 2.1Laguna XS 2.1 Free · Seed Character $0.163 per 1M tokens (3:1 blend) · Ornith 1.0 35B unpriced
  • Longest contextOrnith 1.0 35B and Laguna XS 2.1Ornith 1.0 35B 262,144 · Laguna XS 2.1 262,144 · Seed Character 256,000 tokens
  • Widest inputsSeed CharacterOrnith 1.0 35B: Text, Images · Laguna XS 2.1: Text · Seed Character: Text, Images, Video
  • Self-hostingOrnith 1.0 35B and Laguna XS 2.1Publishes downloadable weights (MIT)
How the score is built
MeasureWeightOrnith 1.0 35BLaguna XS 2.1Seed Character
Inputs & features60%603580
Context window40%434343
Specs & price only100%53/10038/10065/100

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

Ornith 1.0 35B vs Laguna XS 2.1 vs Seed Character specifications side by side
SpecificationOrnith 1.0 35BDeepReinforceLaguna XS 2.1PoolsideSeed CharacterByteDance Seed
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input—Free (best)$0.119
Output—Free (best)$0.297
Cached input——$0.024
Blended (3:1)—Free (best)$0.163
Long-context rate—Same rateOver 32K: $0.178 / $0.891
Price source—Official Poolside APIOfficial Volcengine Ark API
Limits
Context window262,144 tokens (best)262,144 tokens (best)256,000 tokens
Max output—32,768 tokens256,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoYes
ReasoningYesYesYesminimal · low · high
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsOpenMITOpenProprietary
API model ID—poolside/laguna-xs-2.1doubao-seed-character-260628
API providers13 (best)3 (best)
ReleasedJun 25, 2026Jul 2, 2026Jun 23, 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.

  • Ornith 1.0 35B—
  • Laguna XS 2.1Free
  • Seed Character$1.78
04 — Questions

Which should you choose?

Which is better: Ornith 1.0 35B, Laguna XS 2.1 or Seed Character?

There is not enough shared capability evidence to name an overall winner. The scores (Seed Character 65/100, Ornith 1.0 35B 53/100, Laguna XS 2.1 38/100) compare the available specifications and price. 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, Ornith 1.0 35B, Laguna XS 2.1 or Seed Character?

Laguna XS 2.1 is cheaper at Free input / Free output per million tokens (official Poolside API price). Seed Character costs $0.119 input / $0.297 output per million tokens (official Volcengine Ark API price). Laguna XS 2.1 is listed as free. Ornith 1.0 35B has no published per-token price.

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Ornith 1.0 35B has not been scored yet, Laguna XS 2.1 has not been scored yet and Seed Character has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Ornith 1.0 35B, Laguna XS 2.1 and Seed Character 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?

Ornith 1.0 35B and Laguna XS 2.1 have the largest context windows (262,144 and 262,144 tokens), against 256,000 for Seed Character. Maximum output per response: Laguna XS 2.1 up to 32,768, Seed Character up to 256,000 tokens.

Which can read images, PDFs, audio or video?

Ornith 1.0 35B accepts text and images; Laguna XS 2.1 accepts text; Seed Character accepts text, images and video. Seed Character handles the widest range of inputs.

Are any of these open source?

Ornith 1.0 35B and Laguna XS 2.1 publishes its weights (MIT) and can be self-hosted; Seed Character is proprietary.

Which is newer?

Laguna XS 2.1 is the newest, released Jul 2, 2026. Ornith 1.0 35B came out Jun 25, 2026; Seed Character came out Jun 23, 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.