ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Hy3 preview vs Llama 4 Scout 17B Instruct vs Mistral Small 4

Llama 4 Scout 17B Instruct comes out ahead, 71 to 64 and 56 on our weighted score, though Mistral Small 4 is 23% cheaper per token.

  1. Tencent

    Hy3 preview

    Released Apr 20, 2026

    56/100
    • ECI—
    • Price$0.176 / $0.586
    • Context256K
    Full specs Remove Hy3 preview
  2. Our pick

    Meta

    Llama 4 Scout 17B Instruct

    Released Apr 5, 2025

    71/100
    • ECI129.7
    • Price$0.225 / $0.69
    • Context10M
    Full specs Remove Llama 4 Scout 17B Instruct

  3. Mistral AI

    Mistral Small 4

    Released Mar 16, 2026

    64/100
    • ECI—
    • Price$0.15 / $0.60
    • Context256K
    Full specs Remove Mistral Small 4
01 — Verdict

Llama 4 Scout 17B Instruct is our pick

Llama 4 Scout 17B Instruct is the better all-round choice, scoring 71/100 against Mistral Small 4 (64) and Hy3 preview (56). It leads on context window. Mistral Small 4 wins on inputs & features. 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 priceMistral Small 4Mistral Small 4 $0.263 · Hy3 preview $0.279 · Llama 4 Scout 17B Instruct $0.341 per 1M tokens (3:1 blend)
  • Longest contextLlama 4 Scout 17B InstructLlama 4 Scout 17B Instruct 10,000,000 · Hy3 preview 256,000 · Mistral Small 4 256,000 tokens
  • Widest inputsLlama 4 Scout 17B Instruct and Mistral Small 4Hy3 preview: Text · Llama 4 Scout 17B Instruct: Text, Images · Mistral Small 4: Text, Images
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightHy3 previewLlama 4 Scout 17B InstructMistral Small 4
Price50%767277
Inputs & features30%355060
Context window20%3610036
Overall100%56/10071/10064/100

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.

Hy3 preview vs Llama 4 Scout 17B Instruct vs Mistral Small 4 specifications side by side
SpecificationHy3 previewTencentLlama 4 Scout 17B InstructMetaMistral Small 4Mistral AI
Capability
Capabilities Index (ECI)—129.7—
ECI rank—#126 of 148—
GPQA DiamondGraduate-level science questions—51.8%—
OTIS Mock AIME 2024–2025Competition mathematics—7.8%—
Price per million tokens
Input$0.176$0.225$0.15 (best)
Output$0.586 (best)$0.69$0.60
Cached input——$0.015
Blended (3:1)$0.279$0.341$0.263 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 4 providersMedian of 4 providersOfficial Mistral API
Limits
Context window256,000 tokens10,000,000 tokens (best)256,000 tokens
Max output64,000 tokens16,384 tokens256,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYeslow · medium · highNoYeshigh
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenOpenOpen
API model IDhy3-preview—mistral-small-2603
API providers5416 (best)
ReleasedApr 20, 2026Apr 5, 2025Mar 16, 2026
Knowledge cutoff—Aug 2024Jun 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.

  • Hy3 preview$2.93
  • Llama 4 Scout 17B Instruct$3.63
  • Mistral Small 4$2.70
04 — Questions

Which should you choose?

Which is better: Hy3 preview, Llama 4 Scout 17B Instruct or Mistral Small 4?

Llama 4 Scout 17B Instruct is the better all-round choice, scoring 71/100 against Mistral Small 4 (64) and Hy3 preview (56). It leads on context window. Mistral Small 4 wins on inputs & features. 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, Hy3 preview, Llama 4 Scout 17B Instruct or Mistral Small 4?

Mistral Small 4 is cheaper at $0.15 input / $0.60 output per million tokens (official Mistral API price). Hy3 preview costs $0.176 input / $0.586 output per million tokens (median across 4 API providers; free on Tencent TokenHub); Llama 4 Scout 17B Instruct costs $0.225 input / $0.69 output per million tokens (median across 4 API providers). At a typical mix of three input tokens to one output token, that is $0.263 per million tokens for Mistral Small 4 versus $0.279 for Hy3 preview (1.1× as much) and $0.341 for Llama 4 Scout 17B Instruct (1.3× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Hy3 preview has not been scored yet, Llama 4 Scout 17B Instruct has an ECI of 129.7 and Mistral Small 4 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Hy3 preview, Llama 4 Scout 17B Instruct and Mistral Small 4 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?

Llama 4 Scout 17B Instruct has the largest context window at 10,000,000 tokens, against 256,000 for Hy3 preview and 256,000 for Mistral Small 4. Maximum output per response: Hy3 preview up to 64,000, Llama 4 Scout 17B Instruct up to 16,384, Mistral Small 4 up to 256,000 tokens.

Which can read images, PDFs, audio or video?

Hy3 preview accepts text; Llama 4 Scout 17B Instruct accepts text and images; Mistral Small 4 accepts text and images. Llama 4 Scout 17B Instruct handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights, so you can self-host them.

Which is newer?

Hy3 preview is the newest, released Apr 20, 2026. Mistral Small 4 came out Mar 16, 2026; Llama 4 Scout 17B Instruct came out Apr 5, 2025. Knowledge cutoff: Llama 4 Scout 17B Instruct Aug 2024, Mistral Small 4 Jun 2025.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, 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 Oct 4, 2026.

05 — Keep comparing

Related comparisons