The AI arena is free today

Open Superagent

LongCat-Flash-Thinking vs Nemotron Labs Dory 1.0 (4B)

LongCat-Flash-Thinking leads the LLM Stats Score 28.5 to 22.1.

Meituan · NVIDIA · Updated for 2026

Which is better?

LongCat-Flash-Thinking leads the overall LLM Stats Score 28.5 to 22.1, ranking #155 overall.

The models split the 2 individual benchmarks reported for both models evenly.

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

Choose LongCat-Flash-Thinking

  • overall performance matters — it scores 28.5 and ranks #155 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes

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.

LongCat-Flash-Thinking
Meituan
Nemotron Labs Dory 1.0 (4B)
NVIDIA
Core performance indexes
LLM Stats Score
28.5
#155
22.1
#202
Reasoning
28.6
#148
19.8
#213
Coding
13.7
#156
2.9
#241
Agents
12.9
#116
-0.7
#198
Cost, coverage & limits
Benchmark wins
1 of 2
1 of 2
Input price
$0.30 / M
— / M
Output price
$1.20 / M
— / M
Context window
128,000
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
LongCat-Flash-Thinking
Nemotron Labs Dory 1.0 (4B)
Math
28.1#100
12.2#245
Tool use
15.7#100
-2.1#205
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

14 reported for LongCat-Flash-Thinking · 10 for Nemotron Labs Dory 1.0 (4B)

2 shared

LongCat-Flash-Thinking outperforms in 1 benchmarks (GPQA), while Nemotron Labs Dory 1.0 (4B) is better at 1 benchmark (SWE-Bench Verified).

Both models are evenly matched across the benchmarks.

Mon Oct 19 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

556.0B diff

LongCat-Flash-Thinking has 556.0B more parameters than Nemotron Labs Dory 1.0 (4B), making it 13900.0% larger.

Meituan
LongCat-Flash-Thinking
560.0Bparameters
NVIDIA
Nemotron Labs Dory 1.0 (4B)
4.0Bparameters
560.0B
LongCat-Flash-Thinking
4.0B
Nemotron Labs Dory 1.0 (4B)

Context Window

Maximum input and output token capacity

Only LongCat-Flash-Thinking specifies input context (128,000 tokens). Only LongCat-Flash-Thinking specifies output context (128,000 tokens).

Meituan
LongCat-Flash-Thinking
Input128,000 tokens
Output128,000 tokens
NVIDIA
Nemotron Labs Dory 1.0 (4B)
Input- tokens
Output- tokens
Mon Oct 19 2026 • llm-stats.com

License

Usage and distribution terms

LongCat-Flash-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.

LongCat-Flash-Thinking

MIT

Open weights

Nemotron Labs Dory 1.0 (4B)

OpenMDW License v1.1

Open weights

Release Timeline

When each model was launched

LongCat-Flash-Thinking was released on 2025-09-22, while Nemotron Labs Dory 1.0 (4B) was released on 2026-10-16.

Nemotron Labs Dory 1.0 (4B) is 13 months newer than LongCat-Flash-Thinking.

LongCat-Flash-Thinking

Sep 22, 2025

1.1 years ago

Nemotron Labs Dory 1.0 (4B)

Oct 16, 2026

3 days ago

1.1yr 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 LongCat-Flash-Thinking and Nemotron Labs Dory 1.0 (4B) side-by-side, then vote on the output you prefer.

LongCat-Flash-Thinking
✓ Preferred
Nemotron Labs Dory 1.0 (4B)
Open in Playground

FAQ

Common questions about LongCat-Flash-Thinking vs Nemotron Labs Dory 1.0 (4B).

Which is better, LongCat-Flash-Thinking or Nemotron Labs Dory 1.0 (4B)?

LongCat-Flash-Thinking leads the LLM Stats Score 28.5 to 22.1. LongCat-Flash-Thinking is made by Meituan 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 LongCat-Flash-Thinking compare to Nemotron Labs Dory 1.0 (4B) in benchmarks?

LongCat-Flash-Thinking scores MATH-500: 99.2%, ZebraLogic: 95.5%, AIME 2024: 93.3%, AIME 2025: 90.6%, MMLU-Redux: 89.3%. 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 LongCat-Flash-Thinking and Nemotron Labs Dory 1.0 (4B)?

LongCat-Flash-Thinking supports 128K 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 LongCat-Flash-Thinking and Nemotron Labs Dory 1.0 (4B)?

Key differences include LLM Stats Score (28.5 vs 22.1), licensing (MIT vs OpenMDW License v1.1). See the full comparison above for benchmark-by-benchmark results.

Who makes LongCat-Flash-Thinking and Nemotron Labs Dory 1.0 (4B)?

LongCat-Flash-Thinking is developed by Meituan and Nemotron Labs Dory 1.0 (4B) is developed by NVIDIA.

Related comparisons