ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Granite-4.0-H-Micro vs MinerU2.5 2509 1.2B vs Voxtral Mini 3B 2507

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

Price in rating: Excluded · Include price

  1. IBM

    Granite-4.0-H-Micro

    Released Oct 2, 2025

    28/100
    • ECI—
    • Price$0.017 / $0.112
    • Context131K
  2. Opendatalab

    MinerU2.5 2509 1.2B

    Released Sep 17, 2025

    15/100
    • ECI—
    • Price$0.024 / $0.071
    • Context16K
  3. Mistral AI

    Voxtral Mini 3B 2507

    Released Jul 15, 2025

    25/100
    • ECI—
    • Price$0.04 / $0.04
    • Context33K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Granite-4.0-H-Micro 28/100, Voxtral Mini 3B 2507 25/100, MinerU2.5 2509 1.2B 15/100) compare the available specifications only. 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 priceMinerU2.5 2509 1.2BMinerU2.5 2509 1.2B $0.036 · Voxtral Mini 3B 2507 $0.04 · Granite-4.0-H-Micro $0.041 per 1M tokens (3:1 blend)
  • Longest contextGranite-4.0-H-MicroGranite-4.0-H-Micro 131,072 · Voxtral Mini 3B 2507 32,768 · MinerU2.5 2509 1.2B 16,384 tokens
  • Widest inputsMinerU2.5 2509 1.2B and Voxtral Mini 3B 2507Granite-4.0-H-Micro: Text · MinerU2.5 2509 1.2B: Text, Images · Voxtral Mini 3B 2507: Text, Audio
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightGranite-4.0-H-MicroMinerU2.5 2509 1.2BVoxtral Mini 3B 2507
Inputs & features60%252535
Context window40%32011
Specs only100%28/10015/10025/100

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.

Granite-4.0-H-Micro vs MinerU2.5 2509 1.2B vs Voxtral Mini 3B 2507 specifications side by side
SpecificationGranite-4.0-H-MicroIBMMinerU2.5 2509 1.2BOpendatalabVoxtral Mini 3B 2507Mistral AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.017 (best)$0.024$0.04
Output$0.112$0.071$0.04 (best)
Cached input———
Blended (3:1)$0.041$0.036 (best)$0.04
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersMedian of 1 providersMedian of 2 providers
Limits
Context window131,072 tokens (best)16,384 tokens32,768 tokens
Max output131,072 tokens (best)—32,768 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoNoYes
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesNoYes
Structured outputNoNoNo
Availability
WeightsOpenOpenAGPL-3.0OpenApache 2.0
API model ID———
API providers113 (best)
ReleasedOct 2, 2025Sep 17, 2025Jul 15, 2025
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.

  • Granite-4.0-H-Micro$0.394
  • MinerU2.5 2509 1.2B$0.381
  • Voxtral Mini 3B 2507$0.48
04 — Questions

Which should you choose?

Which is better: Granite-4.0-H-Micro, MinerU2.5 2509 1.2B or Voxtral Mini 3B 2507?

There is not enough shared capability evidence to name an overall winner. The scores (Granite-4.0-H-Micro 28/100, Voxtral Mini 3B 2507 25/100, MinerU2.5 2509 1.2B 15/100) compare the available specifications only. 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, Granite-4.0-H-Micro, MinerU2.5 2509 1.2B or Voxtral Mini 3B 2507?

MinerU2.5 2509 1.2B is cheaper at $0.024 input / $0.071 output per million tokens (median across 1 API provider). Voxtral Mini 3B 2507 costs $0.04 input / $0.04 output per million tokens (median across 2 API providers); Granite-4.0-H-Micro costs $0.017 input / $0.112 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.036 per million tokens for MinerU2.5 2509 1.2B versus $0.04 for Voxtral Mini 3B 2507 (1.1× as much) and $0.041 for Granite-4.0-H-Micro (1.1× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Granite-4.0-H-Micro has not been scored yet, MinerU2.5 2509 1.2B has not been scored yet and Voxtral Mini 3B 2507 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Granite-4.0-H-Micro, MinerU2.5 2509 1.2B and Voxtral Mini 3B 2507 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that MinerU2.5 2509 1.2B does not support tool calling, which most coding agents need.

Which has the bigger context window?

Granite-4.0-H-Micro has the largest context window at 131,072 tokens, against 32,768 for Voxtral Mini 3B 2507 and 16,384 for MinerU2.5 2509 1.2B. Maximum output per response: Granite-4.0-H-Micro up to 131,072, Voxtral Mini 3B 2507 up to 32,768 tokens.

Which can read images, PDFs, audio or video?

Granite-4.0-H-Micro accepts text; MinerU2.5 2509 1.2B accepts text and images; Voxtral Mini 3B 2507 accepts text and audio. MinerU2.5 2509 1.2B handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights (AGPL-3.0 and Apache 2.0), so you can self-host them.

Which is newer?

Granite-4.0-H-Micro is the newest, released Oct 2, 2025. MinerU2.5 2509 1.2B came out Sep 17, 2025; Voxtral Mini 3B 2507 came out Jul 15, 2025.

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.