DeepSeek V4 Pro 0813 vs Muse Spark 1.3

At a glance

• Capability index

  • DeepSeek V4 Pro 0813155.3
  • Muse Spark 1.3156.8

  Muse Spark 1.3 is 1.4 points higher.

• Price per 1M tokens

  • DeepSeek V4 Pro 0813$1.98
  • Muse Spark 1.3$2.00

  DeepSeek V4 Pro 0813 is 1% cheaper.

• Context window

  • DeepSeek V4 Pro 08131M tokens
  • Muse Spark 1.31M tokens

  They take in about the same.

• Released

  • DeepSeek V4 Pro 0813Aug 12, 2026
  • Muse Spark 1.3Sep 2, 2026

  Muse Spark 1.3 is 21 days newer.

Where each scores higher

On the 12 tests both have taken, each on its own scale. A gap of a point or two can sit within a test’s margin of error.

10 more tests have results for only one of them; the table below lists every result.

Everything side by side

Comparison of DeepSeek V4 Pro 0813 vs Muse Spark 1.3

Measure	DeepSeek V4 Pro 0813DeepSeek	Muse Spark 1.3Meta AI
Model
Maker	DeepSeek	Meta AI
Sold here by	CrofAI	DevPass (LLM Gateway)
API model ID	deepseek-v4-pro-0813	muse-spark-1.3
Released	Aug 12, 2026	Sep 2, 2026
Knowledge cutoff	Not reported	Not reported
Weights	Open: downloadable	Closed: hosted access only
Developer’s country	China	United States
Hosts selling it	42	11
Training compute	9.7 × 10²⁴ FLOPEpoch AI estimate	Not published
Test results
Capability index	155.3#29 of 274	156.8 (best of these models)#19 of 274
LiveBench overall	77.4%#23 of 66	81.6% (best of these models)#7 of 66
Arena text	Not tested	1494#9 of 413
LiveBench coding	77.2%#38 of 66	81.1% (best of these models)#17 of 66
Arena WebDev	Not tested	1657#14 of 138
Arena coding	Not tested	1539#11 of 408
LiveBench mathematics	95.1%#16 of 66	96.0% (best of these models)#12 of 66
Mock AIME 2024–2025	98.6%#20 of 297	99.2% (best of these models)#15 of 297
FrontierMath Tiers 1–3	64.6%#32 of 114	74.4% (best of these models)#19 of 114
FrontierMath Tier 4	26.8%#39 of 70	46.3% (best of these models)#25 of 70
Arena math	Not tested	1509#9 of 396
SimpleQA Verified	52.9%#21 of 86	Not tested
LiveBench agentic coding	55.0%#28 of 66	64.1% (best of these models)#9 of 66
CursorBench	Not tested	41.6%#22 of 62
LiveBench language	82.1%#26 of 66	82.8% (best of these models)#24 of 66
LiveBench instructions	67.7%#36 of 66	78.0% (best of these models)#4 of 66
Arena creative writing	Not tested	1459#28 of 411
Arena instruction following	Not tested	1486#16 of 413
LiveBench data analysis	79.2%#18 of 66	79.6% (best of these models)#12 of 66
LiveBench reasoning	85.8%#34 of 66	89.7% (best of these models)#15 of 66
GPQA Diamond	91.7%#29 of 319	Not tested
Chess puzzles	47.0% (best of these models)#14 of 227	38.0%#32 of 227
Arena hard prompts	Not tested	1517#10 of 413
Price per million tokens
Input	$0.35 (best of these models)	$1.25
Output	$0.80 (best of these models)	$4.25
Blended, 3 input to 1 output	$0.462 (best of these models)	$2.00
Cached input	$0.01 (best of these models)	$0.15
Limits
Context window	1M tokens	1M tokens
Max input	1M tokens	1M tokens
Max output	131.1K tokens	131.1K tokens
Features
Reads	text	audio, images, PDFs, text and video
Produces	text	text
Reasoning	Yeseffort none, low, high, max; can be switched off; thinking budget can be set	Yeseffort minimal, low, medium, high, xhigh
Tool calling	Yes	Yes
Structured output	Yes, such as JSON	Yes, such as JSON
File attachments	No	Yes
Temperature setting	Supported	Supported

Bold marks the better value in each row. Prices are each model’s own list price, or the middle price across hosts when the maker does not sell it, blended as three input tokens for every output token. Test results as published by LiveBench (Apache-2.0), Epoch AI (CC BY 4.0), Cursor CursorBench, compiled by Epoch AI (CC BY 4.0), Arena (CC BY 4.0); model details and prices from models.dev (MIT). Confirm pricing with the provider before use.