The AI arena is free today

Open Superagent

DeepSeek-V3.2 (Thinking) vs Nemotron Labs Dory 1.0 (4B)

DeepSeek-V3.2 (Thinking) leads the LLM Stats Score 32.2 to 21.8.

DeepSeek · NVIDIA · Updated for 2026

Which is better?

DeepSeek-V3.2 (Thinking) leads the overall LLM Stats Score 32.2 to 21.8, ranking #127 overall.

In the 3 individual benchmarks reported for both models, DeepSeek-V3.2 (Thinking) 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 DeepSeek-V3.2 (Thinking)

  • overall performance matters — it scores 32.2 and ranks #127 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 3 of 3 exact shared results

Choose Nemotron Labs Dory 1.0 (4B)

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

At a glance

The differences that matter most.

DeepSeek-V3.2 (Thinking)
DeepSeek
Nemotron Labs Dory 1.0 (4B)
NVIDIA
Core performance indexes
LLM Stats Score
32.2
#127
21.8
#203
Reasoning
32.2
#124
19.6
#216
Coding
22.7
#97
2.8
#244
Agents
10.9
#135
-1.8
#203
Cost, coverage & limits
Benchmark wins
3 of 3
0 of 3
Input price
$0.28 / M
— / M
Output price
$0.42 / M
— / M
Context window
131,072
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
DeepSeek-V3.2 (Thinking)
Nemotron Labs Dory 1.0 (4B)
Math
30.0#83
12.1#246
Tool use
9.8#146
-2.2#206
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

14 reported for DeepSeek-V3.2 (Thinking) · 10 for Nemotron Labs Dory 1.0 (4B)

3 shared

DeepSeek-V3.2 (Thinking) outperforms in 3 benchmarks (GPQA, Humanity's Last Exam, SWE-Bench Verified), while Nemotron Labs Dory 1.0 (4B) is better at 0 benchmarks.

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks.

Sat Oct 24 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

681.0B diff

DeepSeek-V3.2 (Thinking) has 681.0B more parameters than Nemotron Labs Dory 1.0 (4B), making it 17025.0% larger.

DeepSeek
DeepSeek-V3.2 (Thinking)
685.0Bparameters
NVIDIA
Nemotron Labs Dory 1.0 (4B)
4.0Bparameters
685.0B
DeepSeek-V3.2 (Thinking)
4.0B
Nemotron Labs Dory 1.0 (4B)

Context Window

Maximum input and output token capacity

Only DeepSeek-V3.2 (Thinking) specifies input context (131,072 tokens). Only DeepSeek-V3.2 (Thinking) specifies output context (65,536 tokens).

DeepSeek
DeepSeek-V3.2 (Thinking)
Input131,072 tokens
Output65,536 tokens
NVIDIA
Nemotron Labs Dory 1.0 (4B)
Input- tokens
Output- tokens
Sat Oct 24 2026 • llm-stats.com

License

Usage and distribution terms

DeepSeek-V3.2 (Thinking) is licensed under MIT, while Nemotron Labs Dory 1.0 (4B) uses OpenMDW License v1.1.

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

DeepSeek-V3.2 (Thinking)

MIT

Open weights

Nemotron Labs Dory 1.0 (4B)

OpenMDW License v1.1

Open weights

Release Timeline

When each model was launched

DeepSeek-V3.2 (Thinking) was released on 2025-12-01, while Nemotron Labs Dory 1.0 (4B) was released on 2026-10-16.

Nemotron Labs Dory 1.0 (4B) is 11 months newer than DeepSeek-V3.2 (Thinking).

DeepSeek-V3.2 (Thinking)

Dec 1, 2025

10 months ago

Nemotron Labs Dory 1.0 (4B)

Oct 16, 2026

3 days ago

10mo 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 DeepSeek-V3.2 (Thinking) and Nemotron Labs Dory 1.0 (4B) side-by-side, then vote on the output you prefer.

DeepSeek-V3.2 (Thinking)
✓ Preferred
Nemotron Labs Dory 1.0 (4B)
Open in Playground

FAQ

Common questions about DeepSeek-V3.2 (Thinking) vs Nemotron Labs Dory 1.0 (4B).

Which is better, DeepSeek-V3.2 (Thinking) or Nemotron Labs Dory 1.0 (4B)?

DeepSeek-V3.2 (Thinking) leads the LLM Stats Score 32.2 to 21.8. DeepSeek-V3.2 (Thinking) is made by DeepSeek and Nemotron Labs Dory 1.0 (4B) is made by NVIDIA. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does DeepSeek-V3.2 (Thinking) compare to Nemotron Labs Dory 1.0 (4B) in benchmarks?

DeepSeek-V3.2 (Thinking) scores AIME 2025: 93.1%, HMMT 2025: 90.2%, MMLU-Pro: 85.0%, LiveCodeBench: 83.3%, GPQA: 82.4%. Nemotron Labs Dory 1.0 (4B) scores IFBench: 77.9%, GPQA: 72.4%, AA-LCR: 71.0%, SWE-Bench Verified: 59.5%, SciCode: 34.9%.

What are the context window sizes for DeepSeek-V3.2 (Thinking) and Nemotron Labs Dory 1.0 (4B)?

DeepSeek-V3.2 (Thinking) supports 131K tokens and Nemotron Labs Dory 1.0 (4B) supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between DeepSeek-V3.2 (Thinking) and Nemotron Labs Dory 1.0 (4B)?

Key differences include LLM Stats Score (32.2 vs 21.8), licensing (MIT vs OpenMDW License v1.1). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek-V3.2 (Thinking) and Nemotron Labs Dory 1.0 (4B)?

DeepSeek-V3.2 (Thinking) is developed by DeepSeek and Nemotron Labs Dory 1.0 (4B) is developed by NVIDIA.

Related comparisons