Nemotron 3 Super (120B A12B) vs Qwen3-Next-80B-A3B-Thinking

Nemotron 3 Super (120B A12B) and Qwen3-Next-80B-A3B-Thinking are closely matched at 26.1 and 23.2 on the LLM Stats Score. Nemotron 3 Super (120B A12B) is 3.0x cheaper per token.

NVIDIA · Alibaba Cloud / Qwen Team · Updated for 2026

Which is better?

Nemotron 3 Super (120B A12B) and Qwen3-Next-80B-A3B-Thinking are closely matched on the overall LLM Stats Score at 26.1 and 23.2.

In the 8 individual benchmarks reported for both models, Nemotron 3 Super (120B A12B) wins 6; this is a narrower head-to-head signal than the composite indexes.

On price, Nemotron 3 Super (120B A12B) is roughly 3.0x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Nemotron 3 Super (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 Nemotron 3 Super (120B A12B)

you value its reported benchmark strengths — it wins 6 of 8 exact shared results
cost matters — it's about 3.0x cheaper per token
you process long inputs — it offers a 262,144 token context window
you want the most recent training data — it shipped Mar 2026

Choose Qwen3-Next-80B-A3B-Thinking

your work emphasizes agents — it leads those capability indexes

At a glance

The differences that matter most.

Better token value: Nemotron 3 Super (120B A12B)

Nemotron 3 Super (120B A12B)

NVIDIA

Qwen3-Next-80B-A3B-Thinking

Alibaba Cloud / Qwen Team

Core performance indexes

LLM Stats Score

26.1

#182 · 23 evals

Best

23.2

#208 · 22 evals

Reasoning

24.4

#189 · 20 evals

Best

23.9

#192 · 18 evals

Agents

-1.3

#213 · 3 evals

12.0

#136 · 1 evals

Best

Cost, coverage & limits

Benchmark wins

6 of 8

Best

2 of 8

Input price

$0.09 / M

Best

$0.15 / M

Output price

$0.40 / M

Best

$1.50 / M

Context window

262,144

Best

65,536

Capability indexes

Additional strengths measured across groups of related public benchmarks

5 shared

Index

Nemotron 3 Super (120B A12B)

Qwen3-Next-80B-A3B-Thinking

Math

29.9#88 · 6 evals

26.4#113 · 8 evals

Tool use

2.3#199 · 4 evals

10.6#146 · 6 evals

Writing

9.5#82 · 4 evals

13.8#54 · 7 evals

Finance

27.1#40 · 2 evals

27.8#37 · 5 evals

Legal

27.1#27 · 2 evals

26.2#40 · 4 evals

Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

23 reported for Nemotron 3 Super (120B A12B) · 23 for Qwen3-Next-80B-A3B-Thinking

8 shared

Nemotron 3 Super (120B A12B) outperforms in 6 benchmarks (AIME 2025, Arena-Hard v2, GPQA, MMLU-Pro, MMLU-ProX, Tau2 Telecom), while Qwen3-Next-80B-A3B-Thinking is better at 2 benchmarks (Tau2 Airline, Tau2 Retail).

Nemotron 3 Super (120B A12B) shows notably better performance in the majority of benchmarks.

Thu Nov 05 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Nemotron 3 Super (120B A12B) costs less

For input processing, Nemotron 3 Super (120B A12B) ($0.09/1M tokens) is 1.8x cheaper than Qwen3-Next-80B-A3B-Thinking ($0.15/1M tokens).

For output processing, Nemotron 3 Super (120B A12B) ($0.40/1M tokens) is 3.8x cheaper than Qwen3-Next-80B-A3B-Thinking ($1.50/1M tokens).

In conclusion, Qwen3-Next-80B-A3B-Thinking is more expensive than Nemotron 3 Super (120B A12B).*

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

Lowest available price from all providers

Thu Nov 05 2026 • llm-stats.com

Nemotron 3 Super (120B A12B)

Input tokens$0.09

Output tokens$0.40

Best providerDeepinfra

Qwen3-Next-80B-A3B-Thinking

Input tokens$0.15

Output tokens$1.50

Best providerNovita

Notice missing or incorrect data?

Model Size

Parameter count comparison

40.0B diff

Nemotron 3 Super (120B A12B) has 40.0B more parameters than Qwen3-Next-80B-A3B-Thinking, making it 50.0% larger.

Nemotron 3 Super (120B A12B)

120.0Bparameters

Qwen3-Next-80B-A3B-Thinking

80.0Bparameters

120.0B

Nemotron 3 Super (120B A12B)

80.0B

Qwen3-Next-80B-A3B-Thinking

Context Window

Maximum input and output token capacity

Nemotron 3 Super (120B A12B) accepts 262,144 input tokens compared to Qwen3-Next-80B-A3B-Thinking's 65,536 tokens. Nemotron 3 Super (120B A12B) can generate longer responses up to 262,144 tokens, while Qwen3-Next-80B-A3B-Thinking is limited to 65,536 tokens.

Nemotron 3 Super (120B A12B)

Input262,144 tokens

Output262,144 tokens

Qwen3-Next-80B-A3B-Thinking

Input65,536 tokens

Output65,536 tokens

Thu Nov 05 2026 • llm-stats.com

License

Usage and distribution terms

Nemotron 3 Super (120B A12B) is licensed under NVIDIA Open Model License Agreement , while Qwen3-Next-80B-A3B-Thinking uses Apache 2.0.

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

Nemotron 3 Super (120B A12B)

NVIDIA Open Model License Agreement

Open weights

Qwen3-Next-80B-A3B-Thinking

Apache 2.0

Open weights

Release Timeline

When each model was launched

Nemotron 3 Super (120B A12B) was released on 2026-03-11, while Qwen3-Next-80B-A3B-Thinking was released on 2025-09-10.

Nemotron 3 Super (120B A12B) is 6 months newer than Qwen3-Next-80B-A3B-Thinking.

Nemotron 3 Super (120B A12B)

Mar 11, 2026

7 months ago

6mo newer

Qwen3-Next-80B-A3B-Thinking

Sep 10, 2025

1.2 years ago

Knowledge Cutoff

When training data ends

Nemotron 3 Super (120B A12B) has a documented knowledge cutoff of 2025-06-01, while Qwen3-Next-80B-A3B-Thinking'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 Qwen3-Next-80B-A3B-Thinking's cutoff date.

Nemotron 3 Super (120B A12B)

Jun 2025

Qwen3-Next-80B-A3B-Thinking

—

Provider Availability

Nemotron 3 Super (120B A12B) is available from DeepInfra. Qwen3-Next-80B-A3B-Thinking is available from Novita.

Nemotron 3 Super (120B A12B)

Deepinfra

Input Price:Input: $0.09/1MOutput Price:Output: $0.40/1M

Qwen3-Next-80B-A3B-Thinking

Novita

Input Price:Input: $0.15/1MOutput Price:Output: $1.50/1M

* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Nemotron 3 Super (120B A12B) and Qwen3-Next-80B-A3B-Thinking side-by-side, then vote on the output you prefer.

Nemotron 3 Super (120B A12B)

✓ Preferred

Qwen3-Next-80B-A3B-Thinking

Open in Playground

FAQ

Common questions about Nemotron 3 Super (120B A12B) vs Qwen3-Next-80B-A3B-Thinking.

Which is better, Nemotron 3 Super (120B A12B) or Qwen3-Next-80B-A3B-Thinking?

Nemotron 3 Super (120B A12B) and Qwen3-Next-80B-A3B-Thinking are closely matched on the LLM Stats Score at 26.1 and 23.2. Nemotron 3 Super (120B A12B) is made by NVIDIA and Qwen3-Next-80B-A3B-Thinking is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Nemotron 3 Super (120B A12B) compare to Qwen3-Next-80B-A3B-Thinking in benchmarks?

Nemotron 3 Super (120B A12B) scores HMMT 2025: 94.7%, RULER: 91.8%, AIME 2025: 90.2%, WMT24++: 86.7%, MMLU-Pro: 83.7%. Qwen3-Next-80B-A3B-Thinking scores MMLU-Redux: 92.5%, IFEval: 88.9%, AIME 2025: 87.8%, WritingBench: 84.6%, MMLU-Pro: 82.7%.

Is Nemotron 3 Super (120B A12B) cheaper than Qwen3-Next-80B-A3B-Thinking?

Nemotron 3 Super (120B A12B) is 1.8x cheaper for input tokens. Nemotron 3 Super (120B A12B) costs $0.09/M input and $0.40/M output via deepinfra. Qwen3-Next-80B-A3B-Thinking costs $0.15/M input and $1.50/M output via novita.

What are the context window sizes for Nemotron 3 Super (120B A12B) and Qwen3-Next-80B-A3B-Thinking?

Nemotron 3 Super (120B A12B) supports 262K tokens and Qwen3-Next-80B-A3B-Thinking supports 66K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Nemotron 3 Super (120B A12B) and Qwen3-Next-80B-A3B-Thinking?

Key differences include LLM Stats Score (26.1 vs 23.2), context window (262K vs 66K), input pricing ($0.09 vs $0.15/M), licensing (NVIDIA Open Model License Agreement vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Nemotron 3 Super (120B A12B) and Qwen3-Next-80B-A3B-Thinking?

Nemotron 3 Super (120B A12B) is developed by NVIDIA and Qwen3-Next-80B-A3B-Thinking is developed by Alibaba Cloud / Qwen Team.

Nemotron 3 Super (120B A12B) vs Qwen3-Next-80B-A3B-Thinking