ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Gemini 2.5 Flash-Lite vs Granite-4.0-H-Small vs Mistral Nemotron

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

Price in rating: Excluded · Include price

  1. Google

    Gemini 2.5 Flash-Lite

    Released Jun 17, 2025

    86/100
    • ECI—
    • Price$0.10 / $0.40
    • Context1.05M
  2. IBM

    Granite-4.0-H-Small

    Released Oct 2, 2025

    34/100
    • ECI—
    • Price$0.064 / $0.265
    • Context131K
  3. NVIDIA

    Mistral Nemotron

    Released Jun 11, 2025

    28/100
    • ECI—
    • Price—
    • Context128K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Gemini 2.5 Flash-Lite 86/100, Granite-4.0-H-Small 34/100, Mistral Nemotron 28/100) 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 priceGranite-4.0-H-SmallGranite-4.0-H-Small $0.114 · Gemini 2.5 Flash-Lite $0.175 per 1M tokens (3:1 blend) · Mistral Nemotron unpriced
  • Longest contextGemini 2.5 Flash-LiteGemini 2.5 Flash-Lite 1,048,576 · Granite-4.0-H-Small 131,072 · Mistral Nemotron 128,000 tokens
  • Widest inputsGemini 2.5 Flash-LiteGemini 2.5 Flash-Lite: Text, Images, PDFs, Audio, Video · Granite-4.0-H-Small: Text · Mistral Nemotron: Text
  • Self-hostingGranite-4.0-H-SmallPublishes downloadable weights
How the score is built
MeasureWeightGemini 2.5 Flash-LiteGranite-4.0-H-SmallMistral Nemotron
Inputs & features60%1003525
Context window40%653232
Specs only100%86/10034/10028/100

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.

Gemini 2.5 Flash-Lite vs Granite-4.0-H-Small vs Mistral Nemotron specifications side by side
SpecificationGemini 2.5 Flash-LiteGoogleGranite-4.0-H-SmallIBMMistral NemotronNVIDIA
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.10$0.064 (best)—
Output$0.40$0.265 (best)—
Cached input$0.01——
Blended (3:1)$0.175$0.114 (best)—
Long-context rateSame rateSame rate—
Price sourceOfficial Google APIOfficial watsonx.ai API—
Limits
Context window1,048,576 tokens (best)131,072 tokens128,000 tokens
Max output65,536 tokens131,072 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsYesNoNo
AudioYesNoNo
VideoYesNoNo
ReasoningYesNoNo
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsProprietaryOpenProprietary
API model IDgemini-2.5-flash-liteibm/granite-4-h-small—
API providers23 (best)1—
ReleasedJun 17, 2025Oct 2, 2025Jun 11, 2025
Knowledge cutoffJan 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.

  • Gemini 2.5 Flash-Lite$1.80
  • Granite-4.0-H-Small$1.17
  • Mistral Nemotron—
04 — Questions

Which should you choose?

Which is better: Gemini 2.5 Flash-Lite, Granite-4.0-H-Small or Mistral Nemotron?

There is not enough shared capability evidence to name an overall winner. The scores (Gemini 2.5 Flash-Lite 86/100, Granite-4.0-H-Small 34/100, Mistral Nemotron 28/100) 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, Gemini 2.5 Flash-Lite, Granite-4.0-H-Small or Mistral Nemotron?

Granite-4.0-H-Small is cheaper at $0.064 input / $0.265 output per million tokens (official watsonx.ai API price). Gemini 2.5 Flash-Lite costs $0.10 input / $0.40 output per million tokens (official Google API price). At a typical mix of three input tokens to one output token, that is $0.114 per million tokens for Granite-4.0-H-Small versus $0.175 for Gemini 2.5 Flash-Lite (1.5× as much). Mistral Nemotron has no published per-token price.

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Gemini 2.5 Flash-Lite has not been scored yet, Granite-4.0-H-Small has not been scored yet and Mistral Nemotron has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Gemini 2.5 Flash-Lite, Granite-4.0-H-Small and Mistral Nemotron 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?

Gemini 2.5 Flash-Lite has the largest context window at 1,048,576 tokens, against 131,072 for Granite-4.0-H-Small and 128,000 for Mistral Nemotron. Maximum output per response: Gemini 2.5 Flash-Lite up to 65,536, Granite-4.0-H-Small up to 131,072, Mistral Nemotron up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Gemini 2.5 Flash-Lite accepts text, images, PDFs, audio and video; Granite-4.0-H-Small accepts text; Mistral Nemotron accepts text. Gemini 2.5 Flash-Lite handles the widest range of inputs.

Are any of these open source?

Granite-4.0-H-Small publishes its weights and can be self-hosted; Gemini 2.5 Flash-Lite and Mistral Nemotron is proprietary.

Which is newer?

Granite-4.0-H-Small is the newest, released Oct 2, 2025. Gemini 2.5 Flash-Lite came out Jun 17, 2025; Mistral Nemotron came out Jun 11, 2025. Knowledge cutoff: Gemini 2.5 Flash-Lite Jan 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.