ZMIME
Comparison · 3 models · Updated Nov 22, 2026

Apertus 8B vs Sarvam 105B vs Granite-4.0-H-Small

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

  1. Swiss AI

    Apertus 8B

    Released Sep 2, 2025

    69/100
    • ECI—
    • Price$0.10 / $0.20
    • Context66K
  2. Sarvam AI

    Sarvam 105B

    Released Feb 18, 2026

    61/100
    • ECI—
    • Price$0.158 / $0.632
    • Context131K
  3. IBM

    Granite-4.0-H-Small

    Released Oct 2, 2025

    74/100
    • ECI—
    • Price$0.064 / $0.265
    • Context131K
  4. Swiss AI

    Apertus 8B

    Released Sep 2, 2025

    22/100
    • ECI—
    • Price$0.10 / $0.20
    • Context66K
  5. Sarvam AI

    Sarvam 105B

    Released Feb 18, 2026

    32/100
    • ECI—
    • Price$0.158 / $0.632
    • Context131K
  6. IBM

    Granite-4.0-H-Small

    Released Oct 2, 2025

    32/100
    • ECI—
    • Price$0.064 / $0.265
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Granite-4.0-H-Small 74/100, Apertus 8B 69/100, Sarvam 105B 61/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (Sarvam 105B 32/100, Granite-4.0-H-Small 32/100, Apertus 8B 22/100) compare the available specifications only. The score weighs context window 100%. 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 · Apertus 8B $0.125 · Sarvam 105B $0.276 per 1M tokens (3:1 blend)
  • Longest contextSarvam 105B and Granite-4.0-H-SmallSarvam 105B 131,072 · Granite-4.0-H-Small 131,072 · Apertus 8B 65,536 tokens
  • Widest inputsSame inputsApertus 8B: Text · Sarvam 105B: Text · Granite-4.0-H-Small: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightApertus 8BSarvam 105BGranite-4.0-H-Small
Price71%897390
Context window29%223232
Specs & price only100%69/10061/10074/100

Left out because at least one model lacks the data: capability and inputs & features. The remaining weights were rescaled.

How the score is built
MeasureWeightApertus 8BSarvam 105BGranite-4.0-H-Small
Context window100%223232
Specs only100%22/10032/10032/100

Left out because at least one model lacks the data: capability and inputs & features. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.

Apertus 8B vs Sarvam 105B vs Granite-4.0-H-Small specifications side by side
SpecificationApertus 8BSwiss AISarvam 105BSarvam AIGranite-4.0-H-SmallIBM
Capability
Capabilities Index (ECI)Not publishedNot publishedNot published
ECI rankNot publishedNot publishedNot published
ECI confidence intervalNot publishedNot publishedNot published
ECI evaluation dateNot publishedNot publishedNot published
Documented capabilitiesFully open 8B multilingual LLM supporting 1800+ languages with 65K context. Trained on compliant open data. Apache 2.0, EU AI Act compliant.Flagship Indian-language reasoning model for enterprise multilingual applicationsOpen-weight hybrid model for enterprise chat, coding, retrieval-augmented generation, and tool-calling workloads
Model parametersNot publishedNot publishedNot published
Output modalitiesTextTextText
Price per million tokens
Input$0.10$0.158$0.064 (best)
Output$0.20 (best)$0.632$0.265
Cached inputNot published$0.053Not published
Blended (3:1)$0.125$0.276$0.114 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersOfficial Sarvam AI APIOfficial watsonx.ai API
Limits
Context window65,536 tokens131,072 tokens (best)131,072 tokens (best)
Max inputNot publishedNot publishedNot published
Max output8,192 tokens131,072 tokens (best)131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoYeslow · medium · highNo
Tool callingYesYesYes
Structured outputNot publishedNot publishedYes
File attachmentsNoNoNo
Temperature controlYesYesYes
Reasoning controlNot publishedeffortNot published
Availability
WeightsOpenApache-2.0OpenOpen
API model IDNot publishedsarvam-105bibm/granite-4-h-small
API providers13 (best)1
ReleasedSep 2, 2025Feb 18, 2026Oct 2, 2025
Knowledge cutoffSep 2025Not publishedNot published
Publisher documentationModel weightsPublisher documentation · Model weightsPublisher documentation · Model weights
Source metadata updatedSep 2, 2025Feb 18, 2026Oct 2, 2025
Data sourcesmodels.dev · Epoch AImodels.dev · Epoch AImodels.dev · Epoch AI
Catalog checkedNov 22, 2026Nov 22, 2026Nov 22, 2026
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.

  • Apertus 8B$1.40
  • Sarvam 105B$2.84
  • Granite-4.0-H-Small$1.17
04 — Questions

Which should you choose?

Which is better: Apertus 8B, Sarvam 105B or Granite-4.0-H-Small?

There is not enough shared capability evidence to name an overall winner. The scores (Granite-4.0-H-Small 74/100, Apertus 8B 69/100, Sarvam 105B 61/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (Sarvam 105B 32/100, Granite-4.0-H-Small 32/100, Apertus 8B 22/100) compare the available specifications only. The score weighs context window 100%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Apertus 8B, Sarvam 105B or Granite-4.0-H-Small?

Granite-4.0-H-Small is cheaper at $0.064 input / $0.265 output per million tokens (official watsonx.ai API price). Apertus 8B costs $0.10 input / $0.20 output per million tokens (median across 1 API provider); Sarvam 105B costs $0.158 input / $0.632 output per million tokens (official Sarvam AI 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 $0.125 for Apertus 8B (1.1× as much) and $0.276 for Sarvam 105B (2.4× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Apertus 8B has not been scored yet, Sarvam 105B has not been scored yet and Granite-4.0-H-Small has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Apertus 8B, Sarvam 105B and Granite-4.0-H-Small 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?

Sarvam 105B and Granite-4.0-H-Small have the largest context windows (131,072 and 131,072 tokens), against 65,536 for Apertus 8B. Maximum output per response: Apertus 8B up to 8,192, Sarvam 105B up to 131,072, Granite-4.0-H-Small up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Apertus 8B accepts text; Sarvam 105B accepts text; Granite-4.0-H-Small accepts text. They handle the same number of input types.

Are any of these open source?

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

Which is newer?

Sarvam 105B is the newest, released Feb 18, 2026. Granite-4.0-H-Small came out Oct 2, 2025; Apertus 8B came out Sep 2, 2025. Knowledge cutoff: Apertus 8B Sep 2025.

How do you decide the winner?

This rating uses price (71%, blended price per million tokens (3 input : 1 output), log scale); context window (29%, 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 22, 2026.This rating uses context window (100%, 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 22, 2026.