The AI arena is free today

Open Superagent

MAI-Thinking-1 vs Nemotron 3.5 Super VL (120B A12B)

MAI-Thinking-1 and Nemotron 3.5 Super VL (120B A12B) are closely matched at 32.8 and 35.0 on the LLM Stats Score.

Microsoft · NVIDIA · Updated for 2026

Which is better?

MAI-Thinking-1 and Nemotron 3.5 Super VL (120B A12B) are closely matched on the overall LLM Stats Score at 32.8 and 35.0.

In the 5 individual benchmarks reported for both models, Nemotron 3.5 Super VL (120B A12B) wins 3; this is a narrower head-to-head signal than the composite indexes.

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

Choose MAI-Thinking-1

  • you are already invested in the Microsoft ecosystem

Choose Nemotron 3.5 Super VL (120B A12B)

  • you value its reported benchmark strengths — it wins 3 of 5 exact shared results
  • you want the most recent training data — it shipped Oct 2026
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

MAI-Thinking-1
Microsoft
Nemotron 3.5 Super VL (120B A12B)
NVIDIA
Core performance indexes
LLM Stats Score
32.8
#122
35.0
#108
Reasoning
33.6
#112
36.2
#94
Coding
19.4
#121
21.0
#108
Agents
12.9
#117
16.5
#99
Cost, coverage & limits
Benchmark wins
2 of 5
3 of 5
Input price
— / M
$0.20 / M
Output price
— / M
$1.00 / M
Context window
—
262,144

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
MAI-Thinking-1
Nemotron 3.5 Super VL (120B A12B)
Math
33.7#54
28.1#101
Tool use
10.7#136
11.0#133
Long context
19.3#36
22.9#17
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

23 reported for MAI-Thinking-1 · 19 for Nemotron 3.5 Super VL (120B A12B)

5 shared

MAI-Thinking-1 outperforms in 2 benchmarks (SWE-Bench Pro, SWE-Bench Verified), while Nemotron 3.5 Super VL (120B A12B) is better at 3 benchmarks (GPQA, IFBench, LiveCodeBench v6).

Nemotron 3.5 Super VL (120B A12B) has a slight edge in benchmark performance.

Tue Oct 20 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

880.0B diff

MAI-Thinking-1 has 880.0B more parameters than Nemotron 3.5 Super VL (120B A12B), making it 733.3% larger.

Microsoft
MAI-Thinking-1
1.0Tparameters
NVIDIA
Nemotron 3.5 Super VL (120B A12B)
120.0Bparameters
1000.0B
MAI-Thinking-1
120.0B
Nemotron 3.5 Super VL (120B A12B)

Context Window

Maximum input and output token capacity

Only Nemotron 3.5 Super VL (120B A12B) specifies input context (262,144 tokens). Only Nemotron 3.5 Super VL (120B A12B) specifies output context (262,144 tokens).

Microsoft
MAI-Thinking-1
Input- tokens
Output- 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

Nemotron 3.5 Super VL (120B A12B) supports multimodal inputs, whereas MAI-Thinking-1 does not.

Nemotron 3.5 Super VL (120B A12B) can handle both text and other forms of data like images, making it suitable for multimodal applications.

MAI-Thinking-1

Text
Images
Audio
Video

Nemotron 3.5 Super VL (120B A12B)

Text
Images
Audio
Video

License

Usage and distribution terms

MAI-Thinking-1 is licensed under a proprietary license, 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.

MAI-Thinking-1

Proprietary

Closed source

Nemotron 3.5 Super VL (120B A12B)

OpenMDW License v1.1

Open weights

Release Timeline

When each model was launched

MAI-Thinking-1 was released on 2026-06-02, while Nemotron 3.5 Super VL (120B A12B) was released on 2026-10-15.

Nemotron 3.5 Super VL (120B A12B) is 5 months newer than MAI-Thinking-1.

MAI-Thinking-1

Jun 2, 2026

4 months ago

Nemotron 3.5 Super VL (120B A12B)

Oct 15, 2026

2 days ago

4mo newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against MAI-Thinking-1 and Nemotron 3.5 Super VL (120B A12B) side-by-side, then vote on the output you prefer.

MAI-Thinking-1
✓ Preferred
Nemotron 3.5 Super VL (120B A12B)
Open in Playground

FAQ

Common questions about MAI-Thinking-1 vs Nemotron 3.5 Super VL (120B A12B).

Which is better, MAI-Thinking-1 or Nemotron 3.5 Super VL (120B A12B)?

MAI-Thinking-1 and Nemotron 3.5 Super VL (120B A12B) are closely matched on the LLM Stats Score at 32.8 and 35.0. MAI-Thinking-1 is made by Microsoft 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 MAI-Thinking-1 compare to Nemotron 3.5 Super VL (120B A12B) in benchmarks?

MAI-Thinking-1 scores LongFact: 98.0%, AIME 2025: 97.0%, AIME 2026: 94.5%, GraphWalks: 90.0%, AIR-Bench: 88.0%. 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%.

What are the context window sizes for MAI-Thinking-1 and Nemotron 3.5 Super VL (120B A12B)?

MAI-Thinking-1 supports an unknown number of 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 MAI-Thinking-1 and Nemotron 3.5 Super VL (120B A12B)?

Key differences include LLM Stats Score (32.8 vs 35.0), multimodal support (no vs yes), licensing (Proprietary vs OpenMDW License v1.1). See the full comparison above for benchmark-by-benchmark results.

Who makes MAI-Thinking-1 and Nemotron 3.5 Super VL (120B A12B)?

MAI-Thinking-1 is developed by Microsoft and Nemotron 3.5 Super VL (120B A12B) is developed by NVIDIA.

Related comparisons