The AI arena is free today

Open Superagent

Granite 3.3 8B Instruct vs Nemotron 3.5 Super VL (120B A12B)

Nemotron 3.5 Super VL (120B A12B) leads the LLM Stats Score 35.0 to 2.1. Nemotron 3.5 Super VL (120B A12B) is 1.3x cheaper per token.

IBM · NVIDIA · Updated for 2026

Which is better?

Nemotron 3.5 Super VL (120B A12B) leads the overall LLM Stats Score 35.0 to 2.1, ranking #108 overall.

On price, Nemotron 3.5 Super VL (120B A12B) is roughly 1.3x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Nemotron 3.5 Super VL (120B A12B) also accepts a larger context window (262,144 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Granite 3.3 8B Instruct

  • you want predictable pricing at $0.50/M input and $0.50/M output

Choose Nemotron 3.5 Super VL (120B A12B)

  • overall performance matters — it scores 35.0 and ranks #108 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • cost matters — it's about 1.3x cheaper per token
  • you process long inputs — it offers a 262,144 token context window
  • you want the most recent training data — it shipped Oct 2026

At a glance

The differences that matter most.

Granite 3.3 8B Instruct
IBM
Nemotron 3.5 Super VL (120B A12B)
NVIDIA
Core performance indexes
LLM Stats Score
2.1
#339
35.0
#108
Reasoning
2.5
#328
36.2
#94
Coding
11.1
#178
21.0
#108
Cost, coverage & limits
Benchmark wins
—
—
Input price
$0.50 / M
$0.20 / M
Output price
$0.50 / M
$1.00 / M
Context window
128,000
262,144

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Granite 3.3 8B Instruct
Nemotron 3.5 Super VL (120B A12B)
Math
2.7#301
28.1#101
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

14 reported for Granite 3.3 8B Instruct · 19 for Nemotron 3.5 Super VL (120B A12B)

No common benchmarks found

Granite 3.3 8B Instruct and Nemotron 3.5 Super VL (120B A12B)don't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Nemotron 3.5 Super VL (120B A12B) costs less

For input processing, Granite 3.3 8B Instruct ($0.50/1M tokens) is 2.5x more expensive than Nemotron 3.5 Super VL (120B A12B) ($0.20/1M tokens).

For output processing, Granite 3.3 8B Instruct ($0.50/1M tokens) is 2.0x cheaper than Nemotron 3.5 Super VL (120B A12B) ($1.00/1M tokens).

In conclusion, Granite 3.3 8B Instruct is more expensive than Nemotron 3.5 Super VL (120B A12B).*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Tue Oct 20 2026 • llm-stats.com
IBM
Granite 3.3 8B Instruct
Input tokens$0.50
Output tokens$0.50
Best providerReplicate
NVIDIA
Nemotron 3.5 Super VL (120B A12B)
Input tokens$0.20
Output tokens$1.00
Best providerDeepinfra
Notice missing or incorrect data?

Model Size

Parameter count comparison

112.0B diff

Nemotron 3.5 Super VL (120B A12B) has 112.0B more parameters than Granite 3.3 8B Instruct, making it 1400.0% larger.

IBM
Granite 3.3 8B Instruct
8.0Bparameters
NVIDIA
Nemotron 3.5 Super VL (120B A12B)
120.0Bparameters
8.0B
Granite 3.3 8B Instruct
120.0B
Nemotron 3.5 Super VL (120B A12B)

Context Window

Maximum input and output token capacity

Nemotron 3.5 Super VL (120B A12B) accepts 262,144 input tokens compared to Granite 3.3 8B Instruct's 128,000 tokens. Nemotron 3.5 Super VL (120B A12B) can generate longer responses up to 262,144 tokens, while Granite 3.3 8B Instruct is limited to 8,192 tokens.

IBM
Granite 3.3 8B Instruct
Input128,000 tokens
Output8,192 tokens
NVIDIA
Nemotron 3.5 Super VL (120B A12B)
Input262,144 tokens
Output262,144 tokens
Tue Oct 20 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Granite 3.3 8B Instruct and Nemotron 3.5 Super VL (120B A12B) support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Granite 3.3 8B Instruct

Text
Images
Audio
Video

Nemotron 3.5 Super VL (120B A12B)

Text
Images
Audio
Video

License

Usage and distribution terms

Granite 3.3 8B Instruct is licensed under Apache 2.0, while Nemotron 3.5 Super VL (120B A12B) uses OpenMDW License v1.1.

License differences may affect how you can use these models in commercial or open-source projects.

Granite 3.3 8B Instruct

Apache 2.0

Open weights

Nemotron 3.5 Super VL (120B A12B)

OpenMDW License v1.1

Open weights

Release Timeline

When each model was launched

Granite 3.3 8B Instruct was released on 2025-04-16, while Nemotron 3.5 Super VL (120B A12B) was released on 2026-10-15.

Nemotron 3.5 Super VL (120B A12B) is 18 months newer than Granite 3.3 8B Instruct.

Granite 3.3 8B Instruct

Apr 16, 2025

1.5 years ago

Nemotron 3.5 Super VL (120B A12B)

Oct 15, 2026

4 days ago

1.5yr newer

Knowledge Cutoff

When training data ends

Granite 3.3 8B Instruct has a documented knowledge cutoff of 2024-04-01, while Nemotron 3.5 Super VL (120B A12B)'s cutoff date is not specified.

We can confirm Granite 3.3 8B Instruct's training data extends to 2024-04-01, but cannot make a direct comparison without Nemotron 3.5 Super VL (120B A12B)'s cutoff date.

Granite 3.3 8B Instruct

Apr 2024

Nemotron 3.5 Super VL (120B A12B)

—

Provider Availability

Granite 3.3 8B Instruct is available from Replicate. Nemotron 3.5 Super VL (120B A12B) is available from DeepInfra.

Granite 3.3 8B Instruct

replicate logo
Replicate
Input Price:Input: $0.50/1MOutput Price:Output: $0.50/1M

Nemotron 3.5 Super VL (120B A12B)

deepinfra logo
Deepinfra
Input Price:Input: $0.20/1MOutput Price:Output: $1.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Granite 3.3 8B Instruct and Nemotron 3.5 Super VL (120B A12B) side-by-side, then vote on the output you prefer.

Granite 3.3 8B Instruct
✓ Preferred
Nemotron 3.5 Super VL (120B A12B)
Open in Playground

FAQ

Common questions about Granite 3.3 8B Instruct vs Nemotron 3.5 Super VL (120B A12B).

Which is better, Granite 3.3 8B Instruct or Nemotron 3.5 Super VL (120B A12B)?

Nemotron 3.5 Super VL (120B A12B) leads the LLM Stats Score 35.0 to 2.1. Granite 3.3 8B Instruct is made by IBM and Nemotron 3.5 Super VL (120B A12B) is made by NVIDIA. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Granite 3.3 8B Instruct compare to Nemotron 3.5 Super VL (120B A12B) in benchmarks?

Granite 3.3 8B Instruct scores HumanEval: 89.7%, AttaQ: 88.5%, HumanEval+: 86.1%, AIME 2024: 81.2%, GSM8k: 80.9%. Nemotron 3.5 Super VL (120B A12B) scores GPQA: 89.5%, LiveCodeBench v6: 88.2%, CharXiv-R: 80.8%, MathVision: 78.2%, BrowseComp: 78.0%.

Is Granite 3.3 8B Instruct cheaper than Nemotron 3.5 Super VL (120B A12B)?

Nemotron 3.5 Super VL (120B A12B) is 2.5x cheaper for input tokens. Granite 3.3 8B Instruct costs $0.50/M input and $0.50/M output via replicate. Nemotron 3.5 Super VL (120B A12B) costs $0.20/M input and $1.00/M output via deepinfra.

What are the context window sizes for Granite 3.3 8B Instruct and Nemotron 3.5 Super VL (120B A12B)?

Granite 3.3 8B Instruct supports 128K tokens and Nemotron 3.5 Super VL (120B A12B) supports 262K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Granite 3.3 8B Instruct and Nemotron 3.5 Super VL (120B A12B)?

Key differences include LLM Stats Score (2.1 vs 35.0), context window (128K vs 262K), input pricing ($0.50 vs $0.20/M), licensing (Apache 2.0 vs OpenMDW License v1.1). See the full comparison above for benchmark-by-benchmark results.

Who makes Granite 3.3 8B Instruct and Nemotron 3.5 Super VL (120B A12B)?

Granite 3.3 8B Instruct is developed by IBM and Nemotron 3.5 Super VL (120B A12B) is developed by NVIDIA.

Related comparisons