DeepSeek V4 Pro 0813 vs MiniMax-M3

At a glance

• Capability index

  • DeepSeek V4 Pro 0813155.3
  • MiniMax-M3146.9

  DeepSeek V4 Pro 0813 is 8.4 points higher.

• Price per 1M tokens

  • DeepSeek V4 Pro 0813$1.98
  • MiniMax-M3$0.525

  MiniMax-M3 is 3.8 times cheaper.

• Context window

  • DeepSeek V4 Pro 08131M tokens
  • MiniMax-M31M tokens

  They take in about the same.

• Released

  • DeepSeek V4 Pro 0813Aug 12, 2026
  • MiniMax-M3Jun 1, 2026

  DeepSeek V4 Pro 0813 is 2 months newer.

Where each scores higher

On the 11 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 MiniMax-M3

Measure	DeepSeek V4 Pro 0813DeepSeek	MiniMax-M3MiniMax
Model
Maker	DeepSeek	MiniMax
Sold here by	CrofAI	MiniMax (minimax.io)
API model ID	deepseek-v4-pro-0813	MiniMax-M3
Released	Aug 12, 2026	Jun 1, 2026
Knowledge cutoff	Not reported	Jan 2025
Weights	Open: downloadable	Open: downloadable
Developer’s country	China	China
Hosts selling it	42	56including MiniMax directly
Training compute	9.7 × 10²⁴ FLOPEpoch AI estimate	Not published
Test results
Capability index	155.3 (best of these models)#29 of 274	146.9#68 of 274
LiveBench overall	77.4% (best of these models)#23 of 66	67.3%#61 of 66
Arena text	Not tested	1440#96 of 413
LiveBench coding	77.2% (best of these models)#38 of 66	68.2%#64 of 66
Arena WebDev	Not tested	1482#58 of 138
Arena coding	Not tested	1494#86 of 408
LiveBench mathematics	95.1% (best of these models)#16 of 66	77.0%#65 of 66
Mock AIME 2024–2025	98.6% (best of these models)#20 of 297	71.1%#133 of 297
FrontierMath Tiers 1–3	64.6%#32 of 114	Not tested
FrontierMath Tier 4	26.8%#39 of 70	Not tested
Arena math	Not tested	1432#102 of 396
SimpleQA Verified	52.9%#21 of 86	Not tested
LiveBench agentic coding	55.0% (best of these models)#28 of 66	40.7%#60 of 66
LiveBench language	82.1% (best of these models)#26 of 66	76.8%#45 of 66
LiveBench instructions	67.7% (best of these models)#36 of 66	57.5%#61 of 66
Arena creative writing	Not tested	1406#99 of 411
Arena instruction following	Not tested	1434#88 of 413
LiveBench data analysis	79.2% (best of these models)#18 of 66	76.2%#34 of 66
LiveBench reasoning	85.8% (best of these models)#34 of 66	74.5%#61 of 66
GPQA Diamond	91.7% (best of these models)#29 of 319	90.9%#34 of 319
Chess puzzles	47.0% (best of these models)#14 of 227	14.0%#113 of 227
Arena hard prompts	Not tested	1463#90 of 413
Price per million tokens
Input	$0.35	$0.30 (best of these models)
Output	$0.80 (best of these models)	$1.20
Blended, 3 input to 1 output	$0.462 (best of these models)	$0.525
Cached input	$0.01 (best of these models)	$0.06
Long requests	No separate price reported	$0.60 in, $2.40 outabove 512K tokens
The maker’s own price	Not sold directly	This listing
Limits
Context window	1M tokens	1M tokens
Max input	1M tokens (best of these models)	512K tokens
Max output	131.1K tokens	512K tokens (best of these models)
Features
Reads	text	images, text and video
Produces	text	text
Reasoning	Yeseffort none, low, high, max; can be switched off; thinking budget can be set	Yeseffort low, medium, high; can be switched off; thinking budget can be set
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), Arena (CC BY 4.0); model details and prices from models.dev (MIT). Confirm pricing with the provider before use.