The AI arena is free today

Open Superagent

Muse Spark 1.3 vs Nemotron 3 Super (120B A12B)

Muse Spark 1.3 leads the LLM Stats Score 55.3 to 26.9. Muse Spark 1.3 is 1.6x cheaper per token.

Meta · NVIDIA · Updated for 2026

Which is better?

Muse Spark 1.3 leads the overall LLM Stats Score 55.3 to 26.9, ranking #5 overall.

On price, Muse Spark 1.3 is roughly 1.6x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Muse Spark 1.3 also accepts a larger context window (1,048,576 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 Muse Spark 1.3

  • overall performance matters — it scores 55.3 and ranks #5 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • cost matters — it's about 1.6x cheaper per token
  • you process long inputs — it offers a 1,048,576 token context window
  • you want the most recent training data — it shipped Sep 2026

Choose Nemotron 3 Super (120B A12B)

  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Muse Spark 1.3
Meta
Nemotron 3 Super (120B A12B)
NVIDIA
Core performance indexes
LLM Stats Score
55.3
#5
26.9
#137
Reasoning
52.8
#7
25.1
#143
Coding
41.7
#10
13.0
#134
Agents
40.4
#4
-1.9
#165
Cost, coverage & limits
Benchmark wins
—
—
Input price
$0.10 / M
$0.10 / M
Output price
$0.20 / M
$0.50 / M
Context window
1,048,576
262,144

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
Muse Spark 1.3
Nemotron 3 Super (120B A12B)
Tool use
35.5#2
3.0#159
Long context
31.7#1
14.9#47
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

11 reported for Muse Spark 1.3 · 23 for Nemotron 3 Super (120B A12B)

No common benchmarks found

Muse Spark 1.3 and Nemotron 3 Super (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

Muse Spark 1.3 costs less

For input processing, Muse Spark 1.3 ($0.10/1M tokens) costs the same as Nemotron 3 Super (120B A12B) ($0.10/1M tokens).

For output processing, Muse Spark 1.3 ($0.20/1M tokens) is 2.5x cheaper than Nemotron 3 Super (120B A12B) ($0.50/1M tokens).

In conclusion, Nemotron 3 Super (120B A12B) is more expensive than Muse Spark 1.3.*

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

Lowest available price from all providers
Fri Sep 04 2026 • llm-stats.com
Meta
Muse Spark 1.3
Input tokens$0.10
Output tokens$0.20
Best providerMeta
NVIDIA
Nemotron 3 Super (120B A12B)
Input tokens$0.10
Output tokens$0.50
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Muse Spark 1.3 accepts 1,048,576 input tokens compared to Nemotron 3 Super (120B A12B)'s 262,144 tokens. Muse Spark 1.3 can generate longer responses up to 943,718 tokens, while Nemotron 3 Super (120B A12B) is limited to 262,144 tokens.

Meta
Muse Spark 1.3
Input1,048,576 tokens
Output943,718 tokens
NVIDIA
Nemotron 3 Super (120B A12B)
Input262,144 tokens
Output262,144 tokens
Fri Sep 04 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Muse Spark 1.3 supports multimodal inputs, whereas Nemotron 3 Super (120B A12B) does not.

Muse Spark 1.3 can handle both text and other forms of data like images, making it suitable for multimodal applications.

Muse Spark 1.3

Text
Images
Audio
Video

Nemotron 3 Super (120B A12B)

Text
Images
Audio
Video

License

Usage and distribution terms

Muse Spark 1.3 is licensed under a proprietary license, while Nemotron 3 Super (120B A12B) uses NVIDIA Open Model License Agreement .

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

Muse Spark 1.3

Proprietary

Closed source

Nemotron 3 Super (120B A12B)

NVIDIA Open Model License Agreement

Open weights

Release Timeline

When each model was launched

Muse Spark 1.3 was released on 2026-09-02, while Nemotron 3 Super (120B A12B) was released on 2026-03-11.

Muse Spark 1.3 is 6 months newer than Nemotron 3 Super (120B A12B).

Muse Spark 1.3

Sep 2, 2026

2 days ago

5mo newer
Nemotron 3 Super (120B A12B)

Mar 11, 2026

5 months ago

Knowledge Cutoff

When training data ends

Nemotron 3 Super (120B A12B) has a documented knowledge cutoff of 2025-06-01, while Muse Spark 1.3's cutoff date is not specified.

We can confirm Nemotron 3 Super (120B A12B)'s training data extends to 2025-06-01, but cannot make a direct comparison without Muse Spark 1.3's cutoff date.

Muse Spark 1.3

—

Nemotron 3 Super (120B A12B)

Jun 2025

Provider Availability

Muse Spark 1.3 is available from Meta Model API. Nemotron 3 Super (120B A12B) is available from DeepInfra.

Muse Spark 1.3

meta logo
Meta
Input Price:Input: $0.10/1MOutput Price:Output: $0.20/1M

Nemotron 3 Super (120B A12B)

deepinfra logo
Deepinfra
Input Price:Input: $0.10/1MOutput Price:Output: $0.50/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Muse Spark 1.3 and Nemotron 3 Super (120B A12B) side-by-side, then vote on the output you prefer.

Muse Spark 1.3
✓ Preferred
Nemotron 3 Super (120B A12B)
Open in Playground

FAQ

Common questions about Muse Spark 1.3 vs Nemotron 3 Super (120B A12B).

Which is better, Muse Spark 1.3 or Nemotron 3 Super (120B A12B)?

Muse Spark 1.3 leads the LLM Stats Score 55.3 to 26.9. Muse Spark 1.3 is made by Meta and Nemotron 3 Super (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 Muse Spark 1.3 compare to Nemotron 3 Super (120B A12B) in benchmarks?

Muse Spark 1.3 scores MRCR v2 (8-needle): 98.5%, MRCR v2 (8-needle, 512K-1M): 98.1%, DeepSearchQA: 89.4%, Terminal-Bench 2.1: 88.8%, DeepSWE 1.1: 75.4%. Nemotron 3 Super (120B A12B) scores HMMT 2025: 94.7%, RULER: 91.8%, AIME 2025: 90.2%, WMT24++: 86.7%, MMLU-Pro: 83.7%.

Is Muse Spark 1.3 cheaper than Nemotron 3 Super (120B A12B)?

Both models cost $0.10 per million input tokens.

What are the context window sizes for Muse Spark 1.3 and Nemotron 3 Super (120B A12B)?

Muse Spark 1.3 supports 1.0M tokens and Nemotron 3 Super (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 Muse Spark 1.3 and Nemotron 3 Super (120B A12B)?

Key differences include LLM Stats Score (55.3 vs 26.9), context window (1.0M vs 262K), multimodal support (yes vs no), licensing (Proprietary vs NVIDIA Open Model License Agreement ). See the full comparison above for benchmark-by-benchmark results.

Who makes Muse Spark 1.3 and Nemotron 3 Super (120B A12B)?

Muse Spark 1.3 is developed by Meta and Nemotron 3 Super (120B A12B) is developed by NVIDIA.

Related comparisons