The AI arena is free today

Open Superagent

Atria Dawn Preview vs Step 3.7 Flash

Atria Dawn Preview leads the LLM Stats Score 52.3 to 30.2.

Shanghai AI Laboratory · StepFun · Updated for 2026

Which is better?

Atria Dawn Preview leads the overall LLM Stats Score 52.3 to 30.2, ranking #10 overall.

In the 2 individual benchmarks reported for both models, Atria Dawn Preview wins 2; 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 Atria Dawn Preview

  • overall performance matters — it scores 52.3 and ranks #10 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 2 of 2 exact shared results
  • you want the most recent training data — it shipped Sep 2026

Choose Step 3.7 Flash

  • you want predictable pricing at $0.20/M input and $1.15/M output

At a glance

The differences that matter most.

Atria Dawn Preview
Shanghai AI Laboratory
Step 3.7 Flash
StepFun
Core performance indexes
LLM Stats Score
52.3
#10
30.2
#120
Reasoning
50.5
#12
30.2
#117
Coding
36.2
#22
19.9
#99
Agents
38.8
#10
13.5
#92
Cost, coverage & limits
Benchmark wins
2 of 2
0 of 2
Input price
— / M
$0.20 / M
Output price
— / M
$1.15 / M
Context window
—
262,144

Individual benchmarks

12 reported for Atria Dawn Preview · 4 for Step 3.7 Flash

2 shared

Atria Dawn Preview outperforms in 2 benchmarks (SWE-Bench Pro, Terminal-Bench 2.1), while Step 3.7 Flash is better at 0 benchmarks.

Atria Dawn Preview significantly outperforms across most benchmarks.

Sun Sep 20 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

546.0B diff

Atria Dawn Preview has 546.0B more parameters than Step 3.7 Flash, making it 275.8% larger.

Shanghai AI Laboratory
Atria Dawn Preview
744.0Bparameters
StepFun
Step 3.7 Flash
198.0Bparameters
744.0B
Atria Dawn Preview
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).

Shanghai AI Laboratory
Atria Dawn Preview
Input- tokens
Output- tokens
StepFun
Step 3.7 Flash
Input262,144 tokens
Output262,144 tokens
Sun Sep 20 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Step 3.7 Flash supports multimodal inputs, whereas Atria Dawn Preview does not.

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

Atria Dawn Preview

Text
Images
Audio
Video

Step 3.7 Flash

Text
Images
Audio
Video

License

Usage and distribution terms

Atria Dawn Preview is licensed under MIT, 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.

Atria Dawn Preview

MIT

Open weights

Step 3.7 Flash

Apache 2.0

Open weights

Release Timeline

When each model was launched

Atria Dawn Preview was released on 2026-09-11, while Step 3.7 Flash was released on 2026-06-10.

Atria Dawn Preview is 3 months newer than Step 3.7 Flash.

Atria Dawn Preview

Sep 11, 2026

1 weeks ago

3mo newer
Step 3.7 Flash

Jun 10, 2026

3 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?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Atria Dawn Preview and Step 3.7 Flash side-by-side, then vote on the output you prefer.

Atria Dawn Preview
✓ Preferred
Step 3.7 Flash
Open in Playground

FAQ

Common questions about Atria Dawn Preview vs Step 3.7 Flash.

Which is better, Atria Dawn Preview or Step 3.7 Flash?

Atria Dawn Preview leads the LLM Stats Score 52.3 to 30.2. Atria Dawn Preview is made by Shanghai AI Laboratory 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 Atria Dawn Preview compare to Step 3.7 Flash in benchmarks?

Atria Dawn Preview scores DeepSearchQA: 96.0%, BrowseComp: 92.5%, CyberGym: 86.5%, MLE-Bench Lite: 86.2%, WideSearch: 81.9%. 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 Atria Dawn Preview and Step 3.7 Flash?

Atria Dawn Preview 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 Atria Dawn Preview and Step 3.7 Flash?

Key differences include LLM Stats Score (52.3 vs 30.2), multimodal support (no vs yes), licensing (MIT vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Atria Dawn Preview and Step 3.7 Flash?

Atria Dawn Preview is developed by Shanghai AI Laboratory and Step 3.7 Flash is developed by StepFun.

Related comparisons