DeepSeek V4.1 Flash vs MiniMax-M3

At a glance

• Capability index

  • DeepSeek V4.1 Flash155.6
  • MiniMax-M3147.1

  DeepSeek V4.1 Flash is 8.4 points higher.

• Price per 1M tokens

  • DeepSeek V4.1 Flash$0.464
  • MiniMax-M3$0.525

  DeepSeek V4.1 Flash is 12% cheaper.

• Context window

  • DeepSeek V4.1 Flash1M tokens
  • MiniMax-M31M tokens

  They take in about the same.

• Released

  • DeepSeek V4.1 FlashSep 10, 2026
  • MiniMax-M3Jun 1, 2026

  DeepSeek V4.1 Flash is 3 months newer.

Where each scores higher

On the 18 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.

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

Everything side by side

Comparison of DeepSeek V4.1 Flash vs MiniMax-M3

Measure	DeepSeek V4.1 FlashDeepSeek	MiniMax-M3MiniMax
Model
Maker	DeepSeek	MiniMax
Sold here by	engy	MiniMax (minimax.io)
API model ID	deepseek-v4.1-flash	MiniMax-M3
Released	Sep 10, 2026	Jun 1, 2026
Knowledge cutoff	May 2025	Jan 2025
Weights	Open: downloadable	Open: downloadable
Developer’s country	China	China
Hosts selling it	80	60including MiniMax directly
Training compute	4.3 × 10²⁴ FLOPEpoch AI estimate	Not published
Test results
Capability index	155.6 (best of these models)#31 of 277	147.1#70 of 277
LiveBench overall	81.1% (best of these models)#9 of 70	67.3%#65 of 70
Arena text	1475 (best of these models)#38 of 415	1441#96 of 415
LiveBench coding	80.0% (best of these models)#23 of 70	68.2%#68 of 70
Arena WebDev	1619 (best of these models)#24 of 142	1482#62 of 142
Arena coding	1526 (best of these models)#27 of 410	1496#87 of 410
LiveBench mathematics	93.3% (best of these models)#23 of 70	77.0%#69 of 70
Mock AIME 2024–2025	98.3% (best of these models)#24 of 303	71.1%#139 of 303
FrontierMath Tiers 1–3	67.4%#30 of 117	Not tested
FrontierMath Tier 4	26.8%#41 of 73	Not tested
Arena math	1495 (best of these models)#22 of 400	1430#108 of 400
SimpleQA Verified	42.9%#43 of 90	Not tested
LiveBench agentic coding	77.3% (best of these models)#1 of 70	40.7%#64 of 70
LiveBench language	81.2% (best of these models)#29 of 70	76.8%#46 of 70
LiveBench instructions	70.0% (best of these models)#32 of 70	57.5%#64 of 70
Arena creative writing	1439 (best of these models)#61 of 413	1406#103 of 413
Arena instruction following	1477 (best of these models)#24 of 415	1435#89 of 415
LiveBench data analysis	79.3% (best of these models)#18 of 70	76.2%#36 of 70
LiveBench reasoning	86.7% (best of these models)#32 of 70	74.5%#65 of 70
GPQA Diamond	89.8%#50 of 323	90.9% (best of these models)#35 of 323
Chess puzzles	48.0% (best of these models)#20 of 243	13.0%#134 of 243
Arena hard prompts	1499 (best of these models)#36 of 415	1464#90 of 415
Price per million tokens
Input	$0.04 (best of these models)	$0.30
Output	$0.08 (best of these models)	$1.20
Blended, 3 input to 1 output	$0.05 (best of these models)	$0.525
Cached input	$0.008 (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	327.7K tokens	1M tokens (best of these models)
Max input	1M tokens (best of these models)	512K tokens
Max output	65.5K tokens	512K tokens (best of these models)
Features
Reads	images and 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	Yes	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.