The AI arena is free today

Open Superagent

MiniMax M3 vs Nemotron 3 Ultra (550B A55B)

MiniMax M3 leads the LLM Stats Score 41.4 to 36.3. MiniMax M3 is 1.9x cheaper per token.

MiniMax · NVIDIA · Updated for 2026

Which is better?

MiniMax M3 leads the overall LLM Stats Score 41.4 to 36.3, ranking #51 overall.

In the 4 individual benchmarks reported for both models, MiniMax M3 wins 4; this is a narrower head-to-head signal than the composite indexes.

On price, MiniMax M3 is roughly 1.9x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

MiniMax M3 also accepts a larger context window (524,288 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 MiniMax M3

  • overall performance matters — it scores 41.4 and ranks #51 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 4 of 4 exact shared results
  • cost matters — it's about 1.9x cheaper per token
  • you process long inputs — it offers a 524,288 token context window

Choose Nemotron 3 Ultra (550B A55B)

  • you want the most recent training data — it shipped Jun 2026

At a glance

The differences that matter most.

Core performance indexes
41.4
#51
36.3
#79
41.4
#49
35.4
#82
32.0
#40
21.0
#93
26.3
#49
12.5
#101
Cost, coverage & limits
Benchmark wins
4 of 4
0 of 4
Input price
$0.28 / M
$0.50 / M
Output price
$1.10 / M
$2.20 / M
Context window
524,288
262,144

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
MiniMax M3
Nemotron 3 Ultra (550B A55B)
25.6#107
36.4#39
21.4#52
2.8#166
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

35 reported for MiniMax M3 · 26 for Nemotron 3 Ultra (550B A55B)

4 shared

MiniMax M3 outperforms in 4 benchmarks (BrowseComp, Finance Agent v2, SWE-Bench Verified, Terminal-Bench 2.1), while Nemotron 3 Ultra (550B A55B) is better at 0 benchmarks.

MiniMax M3 significantly outperforms across most benchmarks.

Thu Sep 17 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

MiniMax M3 costs less

For input processing, MiniMax M3 ($0.28/1M tokens) is 1.8x cheaper than Nemotron 3 Ultra (550B A55B) ($0.50/1M tokens).

For output processing, MiniMax M3 ($1.10/1M tokens) is 2.0x cheaper than Nemotron 3 Ultra (550B A55B) ($2.20/1M tokens).

In conclusion, Nemotron 3 Ultra (550B A55B) is more expensive than MiniMax M3.*

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

Lowest available price from all providers
Thu Sep 17 2026 • llm-stats.com
MiniMax
MiniMax M3
Input tokens$0.28
Output tokens$1.10
Best providerDeepinfra
NVIDIA
Nemotron 3 Ultra (550B A55B)
Input tokens$0.50
Output tokens$2.20
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue

Model Size

Parameter count comparison

122.0B diff

Nemotron 3 Ultra (550B A55B) has 122.0B more parameters than MiniMax M3, making it 28.5% larger.

MiniMax
MiniMax M3
428.0Bparameters
NVIDIA
Nemotron 3 Ultra (550B A55B)
550.0Bparameters
428.0B
MiniMax M3
550.0B
Nemotron 3 Ultra (550B A55B)

Context Window

Maximum input and output token capacity

MiniMax M3 accepts 524,288 input tokens compared to Nemotron 3 Ultra (550B A55B)'s 262,144 tokens. MiniMax M3 can generate longer responses up to 524,288 tokens, while Nemotron 3 Ultra (550B A55B) is limited to 262,144 tokens.

MiniMax
MiniMax M3
Input524,288 tokens
Output524,288 tokens
NVIDIA
Nemotron 3 Ultra (550B A55B)
Input262,144 tokens
Output262,144 tokens
Thu Sep 17 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

MiniMax M3 supports multimodal inputs, whereas Nemotron 3 Ultra (550B A55B) does not.

MiniMax M3 can handle both text and other forms of data like images, making it suitable for multimodal applications.

MiniMax M3

Text
Images
Audio
Video

Nemotron 3 Ultra (550B A55B)

Text
Images
Audio
Video

License

Usage and distribution terms

MiniMax M3 is licensed under MIT, while Nemotron 3 Ultra (550B A55B) uses OpenMDW License v1.1.

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

MiniMax M3

MIT

Open weights

Nemotron 3 Ultra (550B A55B)

OpenMDW License v1.1

Open weights

Release Timeline

When each model was launched

MiniMax M3 was released on 2026-06-01, while Nemotron 3 Ultra (550B A55B) was released on 2026-06-04.

Nemotron 3 Ultra (550B A55B) is 0 month newer than MiniMax M3.

MiniMax M3

Jun 1, 2026

3 months ago

Nemotron 3 Ultra (550B A55B)

Jun 4, 2026

3 months ago

3d newer

Knowledge Cutoff

When training data ends

Nemotron 3 Ultra (550B A55B) has a documented knowledge cutoff of 2025-09-30, while MiniMax M3's cutoff date is not specified.

We can confirm Nemotron 3 Ultra (550B A55B)'s training data extends to 2025-09-30, but cannot make a direct comparison without MiniMax M3's cutoff date.

MiniMax M3

Nemotron 3 Ultra (550B A55B)

Sep 2025

Provider Availability

MiniMax M3 is available from DeepInfra, Fireworks, MiniMax, Novita, Together. Nemotron 3 Ultra (550B A55B) is available from DeepInfra.

MiniMax M3

deepinfra logo
Deepinfra
Input Price:Input: $0.28/1MOutput Price:Output: $1.10/1M
fireworks logo
Fireworks
Input Price:Input: $0.30/1MOutput Price:Output: $1.20/1M
minimax logo
MiniMax
Input Price:Input: $0.30/1MOutput Price:Output: $1.20/1M
novita logo
Novita
Input Price:Input: $0.30/1MOutput Price:Output: $1.20/1M
together logo
Together
Input Price:Input: $0.30/1MOutput Price:Output: $1.20/1M

Nemotron 3 Ultra (550B A55B)

deepinfra logo
Deepinfra
Input Price:Input: $0.50/1MOutput Price:Output: $2.20/1M
* 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 MiniMax M3 and Nemotron 3 Ultra (550B A55B) side-by-side, then vote on the output you prefer.

MiniMax M3
✓ Preferred
Nemotron 3 Ultra (550B A55B)
Open in Playground

FAQ

Common questions about MiniMax M3 vs Nemotron 3 Ultra (550B A55B).

Which is better, MiniMax M3 or Nemotron 3 Ultra (550B A55B)?

MiniMax M3 leads the LLM Stats Score 41.4 to 36.3. MiniMax M3 is made by MiniMax and Nemotron 3 Ultra (550B A55B) is made by NVIDIA. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does MiniMax M3 compare to Nemotron 3 Ultra (550B A55B) in benchmarks?

MiniMax M3 scores OmniDocBench 1.5: 91.6%, SpreadSheetBench-v1: 89.3%, USAMO 2026: 85.7%, Video-MME: 85.4%, VideoMMMU: 84.6%. Nemotron 3 Ultra (550B A55B) scores RULER: 94.7%, IMO-AnswerBench: 92.3%, PinchBench: 90.0%, LiveCodeBench v6: 89.0%, GPQA: 87.0%.

Is MiniMax M3 cheaper than Nemotron 3 Ultra (550B A55B)?

MiniMax M3 is 1.8x cheaper for input tokens. MiniMax M3 costs $0.28/M input and $1.10/M output via deepinfra. Nemotron 3 Ultra (550B A55B) costs $0.50/M input and $2.20/M output via deepinfra.

What are the context window sizes for MiniMax M3 and Nemotron 3 Ultra (550B A55B)?

MiniMax M3 supports 524K tokens and Nemotron 3 Ultra (550B A55B) 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 MiniMax M3 and Nemotron 3 Ultra (550B A55B)?

Key differences include LLM Stats Score (41.4 vs 36.3), context window (524K vs 262K), input pricing ($0.28 vs $0.50/M), multimodal support (yes vs no), licensing (MIT vs OpenMDW License v1.1). See the full comparison above for benchmark-by-benchmark results.

Who makes MiniMax M3 and Nemotron 3 Ultra (550B A55B)?

MiniMax M3 is developed by MiniMax and Nemotron 3 Ultra (550B A55B) is developed by NVIDIA.