The AI arena is free today

Open Superagent

Nemotron Labs Dory 1.0 (4B) vs Step 3.7 Flash

Step 3.7 Flash leads the LLM Stats Score 29.7 to 21.8.

NVIDIA · StepFun · Updated for 2026

Which is better?

Step 3.7 Flash leads the overall LLM Stats Score 29.7 to 21.8, ranking #144 overall.

In the 1 individual benchmarks reported for both models, Step 3.7 Flash wins 1; 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 Nemotron Labs Dory 1.0 (4B)

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

Choose Step 3.7 Flash

  • overall performance matters — it scores 29.7 and ranks #144 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results

At a glance

The differences that matter most.

Nemotron Labs Dory 1.0 (4B)
NVIDIA
Step 3.7 Flash
StepFun
Core performance indexes
LLM Stats Score
21.8
#203
29.7
#144
Reasoning
19.6
#216
29.8
#141
Coding
2.8
#244
19.0
#125
Agents
-1.8
#203
13.1
#116
Cost, coverage & limits
Benchmark wins
0 of 1
1 of 1
Input price
— / M
$0.20 / M
Output price
— / M
$1.15 / M
Context window
—
262,144

Individual benchmarks

10 reported for Nemotron Labs Dory 1.0 (4B) · 4 for Step 3.7 Flash

1 shared

Nemotron Labs Dory 1.0 (4B) outperforms in 0 benchmarks, while Step 3.7 Flash is better at 1 benchmark (Terminal-Bench 2.1).

Step 3.7 Flash significantly outperforms across most benchmarks.

Sun Oct 25 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

194.0B diff

Step 3.7 Flash has 194.0B more parameters than Nemotron Labs Dory 1.0 (4B), making it 4850.0% larger.

NVIDIA
Nemotron Labs Dory 1.0 (4B)
4.0Bparameters
StepFun
Step 3.7 Flash
198.0Bparameters
4.0B
Nemotron Labs Dory 1.0 (4B)
198.0B
Step 3.7 Flash

Context Window

Maximum input and output token capacity

Only Step 3.7 Flash specifies input context (262,144 tokens). Only Step 3.7 Flash specifies output context (262,144 tokens).

NVIDIA
Nemotron Labs Dory 1.0 (4B)
Input- tokens
Output- tokens
StepFun
Step 3.7 Flash
Input262,144 tokens
Output262,144 tokens
Sun Oct 25 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Step 3.7 Flash supports multimodal inputs, whereas Nemotron Labs Dory 1.0 (4B) does not.

Step 3.7 Flash can handle both text and other forms of data like images, making it suitable for multimodal applications.

Nemotron Labs Dory 1.0 (4B)

Text
Images
Audio
Video

Step 3.7 Flash

Text
Images
Audio
Video

License

Usage and distribution terms

Nemotron Labs Dory 1.0 (4B) is licensed under OpenMDW License v1.1, while Step 3.7 Flash uses Apache 2.0.

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

Nemotron Labs Dory 1.0 (4B)

OpenMDW License v1.1

Open weights

Step 3.7 Flash

Apache 2.0

Open weights

Release Timeline

When each model was launched

Nemotron Labs Dory 1.0 (4B) was released on 2026-10-16, while Step 3.7 Flash was released on 2026-06-10.

Nemotron Labs Dory 1.0 (4B) is 4 months newer than Step 3.7 Flash.

Nemotron Labs Dory 1.0 (4B)

Oct 16, 2026

1 weeks ago

4mo newer
Step 3.7 Flash

Jun 10, 2026

4 months ago

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 Nemotron Labs Dory 1.0 (4B) and Step 3.7 Flash side-by-side, then vote on the output you prefer.

Nemotron Labs Dory 1.0 (4B)
✓ Preferred
Step 3.7 Flash
Open in Playground

FAQ

Common questions about Nemotron Labs Dory 1.0 (4B) vs Step 3.7 Flash.

Which is better, Nemotron Labs Dory 1.0 (4B) or Step 3.7 Flash?

Step 3.7 Flash leads the LLM Stats Score 29.7 to 21.8. Nemotron Labs Dory 1.0 (4B) is made by NVIDIA and Step 3.7 Flash is made by StepFun. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Nemotron Labs Dory 1.0 (4B) compare to Step 3.7 Flash in benchmarks?

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%. Step 3.7 Flash scores Terminal-Bench 2.1: 59.5%, SWE-Bench Pro: 56.3%, Humanity's Last Exam (with tools, text-only): 47.2%, GDPval: 45.8%.

What are the context window sizes for Nemotron Labs Dory 1.0 (4B) and Step 3.7 Flash?

Nemotron Labs Dory 1.0 (4B) supports an unknown number of tokens and Step 3.7 Flash 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 Nemotron Labs Dory 1.0 (4B) and Step 3.7 Flash?

Key differences include LLM Stats Score (21.8 vs 29.7), multimodal support (no vs yes), licensing (OpenMDW License v1.1 vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Nemotron Labs Dory 1.0 (4B) and Step 3.7 Flash?

Nemotron Labs Dory 1.0 (4B) is developed by NVIDIA and Step 3.7 Flash is developed by StepFun.

Related comparisons