ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Seed Evolving vs Kimi K2.6 vs Apertus 1.5 70B

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

Price in rating: Included · Exclude price

  1. ByteDance Seed

    Seed Evolving

    Released Jun 23, 2026

    55/100
    • ECI—
    • Price$0.891 / $4.45
    • Context1.02M
  2. Moonshot AI

    Kimi K2.6

    Released Apr 20, 2026

    51/100
    • ECI151.6
    • Price$0.95 / $4.00
    • Context262K
  3. Swiss AI

    Apertus 1.5 70B

    Released Jul 24, 2026

    47/100
    • ECI—
    • Price$1.16 / $3.94
    • Context262K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Seed Evolving 55/100, Kimi K2.6 51/100, Apertus 1.5 70B 47/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. 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 priceKimi K2.6Kimi K2.6 $1.71 · Seed Evolving $1.78 · Apertus 1.5 70B $1.85 per 1M tokens (3:1 blend)
  • Longest contextSeed EvolvingSeed Evolving 1,024,000 · Kimi K2.6 262,144 · Apertus 1.5 70B 262,144 tokens
  • Widest inputsSame inputsSeed Evolving: Text, Images, Video · Kimi K2.6: Text, Images, Video · Apertus 1.5 70B: Text, Images, Audio
  • Self-hostingKimi K2.6 and Apertus 1.5 70BPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightSeed EvolvingKimi K2.6Apertus 1.5 70B
Price50%363736
Inputs & features30%808070
Context window20%654343
Specs & price only100%55/10051/10047/100

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.

Seed Evolving vs Kimi K2.6 vs Apertus 1.5 70B specifications side by side
SpecificationSeed EvolvingByteDance SeedKimi K2.6Moonshot AIApertus 1.5 70BSwiss AI
Capability
Capabilities Index (ECI)—151.6—
ECI rank—#61 of 158—
GPQA DiamondGraduate-level science questions—90.8%—
FrontierMath Tiers 1–3Research-level mathematics—57.2%—
OTIS Mock AIME 2024–2025Competition mathematics—96.1%—
SWE-bench VerifiedFixing real GitHub issues—76.7%—
SimpleQA VerifiedShort factual questions—34.9%—
Price per million tokens
Input$0.891 (best)$0.95$1.16
Output$4.45$4.00$3.94 (best)
Cached input$0.178$0.16 (best)—
Blended (3:1)$1.78$1.71 (best)$1.85
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Volcengine Ark APIOfficial Moonshot AI APIMedian of 1 providers
Limits
Context window1,024,000 tokens (best)262,144 tokens262,144 tokens
Max output256,000 tokens262,144 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoNoNo
AudioNoNoYes
VideoYesYesNo
ReasoningYesminimal · low · medium · high · xhigh · maxYesYes
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsProprietaryOpenOpenApache-2.0
API model IDdoubao-seed-evolvingkimi-k2.6—
API providers264 (best)1
ReleasedJun 23, 2026Apr 20, 2026Jul 24, 2026
Knowledge cutoff—Jan 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.

  • Seed Evolving$17.81
  • Kimi K2.6$17.50
  • Apertus 1.5 70B$19.48
04 — Questions

Which should you choose?

Which is better: Seed Evolving, Kimi K2.6 or Apertus 1.5 70B?

There is not enough shared capability evidence to name an overall winner. The scores (Seed Evolving 55/100, Kimi K2.6 51/100, Apertus 1.5 70B 47/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Seed Evolving, Kimi K2.6 or Apertus 1.5 70B?

Kimi K2.6 is cheaper at $0.95 input / $4.00 output per million tokens (official Moonshot AI API price). Seed Evolving costs $0.891 input / $4.45 output per million tokens (official Volcengine Ark API price); Apertus 1.5 70B costs $1.16 input / $3.94 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $1.71 per million tokens for Kimi K2.6 versus $1.78 for Seed Evolving (1× as much) and $1.85 for Apertus 1.5 70B (1.1× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Seed Evolving has not been scored yet, Kimi K2.6 has an ECI of 151.6 and Apertus 1.5 70B has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Seed Evolving and Apertus 1.5 70B 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?

Seed Evolving has the largest context window at 1,024,000 tokens, against 262,144 for Kimi K2.6 and 262,144 for Apertus 1.5 70B. Maximum output per response: Seed Evolving up to 256,000, Kimi K2.6 up to 262,144, Apertus 1.5 70B up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Seed Evolving accepts text, images and video; Kimi K2.6 accepts text, images and video; Apertus 1.5 70B accepts text, images and audio. They handle the same number of input types.

Are any of these open source?

Kimi K2.6 and Apertus 1.5 70B publishes its weights (Apache-2.0) and can be self-hosted; Seed Evolving is proprietary.

Which is newer?

Apertus 1.5 70B is the newest, released Jul 24, 2026. Seed Evolving came out Jun 23, 2026; Kimi K2.6 came out Apr 20, 2026. Knowledge cutoff: Kimi K2.6 Jan 2025.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.