The AI arena is free today

Open Superagent

Muse Spark 1.3 vs Step-3.5-Flash

Muse Spark 1.3 leads the LLM Stats Score 55.1 to 37.3. Muse Spark 1.3 is 1.4x cheaper per token.

Meta · StepFun · Updated for 2026

Which is better?

Muse Spark 1.3 leads the overall LLM Stats Score 55.1 to 37.3, ranking #4 overall.

On price, Muse Spark 1.3 is roughly 1.4x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Muse Spark 1.3 also accepts a larger context window (1,048,576 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 Muse Spark 1.3

  • overall performance matters — it scores 55.1 and ranks #4 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • cost matters — it's about 1.4x cheaper per token
  • you process long inputs — it offers a 1,048,576 token context window
  • you want the most recent training data — it shipped Sep 2026

Choose Step-3.5-Flash

  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Core performance indexes
55.1
#4
37.3
#67
52.6
#7
37.3
#67
41.9
#9
20.5
#94
40.6
#4
15.5
#83
Cost, coverage & limits
Benchmark wins
Input price
$0.10 / M
$0.10 / M
Output price
$0.20 / M
$0.40 / M
Context window
1,048,576
65,536

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Muse Spark 1.3
Step-3.5-Flash
35.8#2
13.3#95
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

11 reported for Muse Spark 1.3 · 7 for Step-3.5-Flash

No common benchmarks found

Muse Spark 1.3 and Step-3.5-Flashdon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Muse Spark 1.3 costs less

For input processing, Muse Spark 1.3 ($0.10/1M tokens) costs the same as Step-3.5-Flash ($0.10/1M tokens).

For output processing, Muse Spark 1.3 ($0.20/1M tokens) is 2.0x cheaper than Step-3.5-Flash ($0.40/1M tokens).

In conclusion, Step-3.5-Flash is more expensive than Muse Spark 1.3.*

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

Lowest available price from all providers
Tue Sep 08 2026 • llm-stats.com
Meta
Muse Spark 1.3
Input tokens$0.10
Output tokens$0.20
Best providerMeta
StepFun
Step-3.5-Flash
Input tokens$0.10
Output tokens$0.40
Best providerStepFun
Notice missing or incorrect data?Start an Issue

Context Window

Maximum input and output token capacity

Muse Spark 1.3 accepts 1,048,576 input tokens compared to Step-3.5-Flash's 65,536 tokens. Muse Spark 1.3 can generate longer responses up to 943,718 tokens, while Step-3.5-Flash is limited to 8,192 tokens.

Meta
Muse Spark 1.3
Input1,048,576 tokens
Output943,718 tokens
StepFun
Step-3.5-Flash
Input65,536 tokens
Output8,192 tokens
Tue Sep 08 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Muse Spark 1.3 supports multimodal inputs, whereas Step-3.5-Flash does not.

Muse Spark 1.3 can handle both text and other forms of data like images, making it suitable for multimodal applications.

Muse Spark 1.3

Text
Images
Audio
Video

Step-3.5-Flash

Text
Images
Audio
Video

License

Usage and distribution terms

Muse Spark 1.3 is licensed under a proprietary license, while Step-3.5-Flash uses Apache 2.0.

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

Muse Spark 1.3

Proprietary

Closed source

Step-3.5-Flash

Apache 2.0

Open weights

Release Timeline

When each model was launched

Muse Spark 1.3 was released on 2026-09-02, while Step-3.5-Flash was released on 2026-02-02.

Muse Spark 1.3 is 7 months newer than Step-3.5-Flash.

Muse Spark 1.3

Sep 2, 2026

6 days ago

7mo newer
Step-3.5-Flash

Feb 2, 2026

7 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

Provider Availability

Muse Spark 1.3 is available from Meta Model API. Step-3.5-Flash is available from StepFun.

Muse Spark 1.3

meta logo
Meta
Input Price:Input: $0.10/1MOutput Price:Output: $0.20/1M

Step-3.5-Flash

stepfun logo
StepFun
Input Price:Input: $0.10/1MOutput Price:Output: $0.40/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Muse Spark 1.3 and Step-3.5-Flash side-by-side, then vote on the output you prefer.

Muse Spark 1.3
✓ Preferred
Step-3.5-Flash
Open in Playground

FAQ

Common questions about Muse Spark 1.3 vs Step-3.5-Flash.

Which is better, Muse Spark 1.3 or Step-3.5-Flash?

Muse Spark 1.3 leads the LLM Stats Score 55.1 to 37.3. Muse Spark 1.3 is made by Meta and Step-3.5-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 Muse Spark 1.3 compare to Step-3.5-Flash in benchmarks?

Muse Spark 1.3 scores MRCR v2 (8-needle): 98.5%, MRCR v2 (8-needle, 512K-1M): 98.1%, DeepSearchQA: 89.4%, Terminal-Bench 2.1: 88.8%, DeepSWE 1.1: 75.4%. Step-3.5-Flash scores AIME 2025: 97.3%, Tau-bench: 88.2%, LiveCodeBench v6: 86.4%, IMO-AnswerBench: 85.4%, SWE-Bench Verified: 74.4%.

Is Muse Spark 1.3 cheaper than Step-3.5-Flash?

Both models cost $0.10 per million input tokens.

What are the context window sizes for Muse Spark 1.3 and Step-3.5-Flash?

Muse Spark 1.3 supports 1.0M tokens and Step-3.5-Flash 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 Muse Spark 1.3 and Step-3.5-Flash?

Key differences include LLM Stats Score (55.1 vs 37.3), context window (1.0M vs 66K), multimodal support (yes vs no), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Muse Spark 1.3 and Step-3.5-Flash?

Muse Spark 1.3 is developed by Meta and Step-3.5-Flash is developed by StepFun.