Grok 4.6 vs MiniMax-M3

At a glance

• Capability index

  • Grok 4.6156.4
  • MiniMax-M3146.9

  Grok 4.6 is 9.5 points higher.

• Price per 1M tokens

  • Grok 4.6$3.00
  • MiniMax-M3$0.525

  MiniMax-M3 is 5.7 times cheaper.

• Context window

  • Grok 4.6500K tokens
  • MiniMax-M31M tokens

  MiniMax-M3 takes in 2.0 times as much.

• Released

  • Grok 4.6Aug 12, 2026
  • MiniMax-M3Jun 1, 2026

  Grok 4.6 is 2 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.

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

Everything side by side

Comparison of Grok 4.6 vs MiniMax-M3

Measure	Grok 4.6xAI	MiniMax-M3MiniMax
Model
Maker	xAI	MiniMax
Sold here by	xAI	MiniMax (minimax.io)
API model ID	grok-4.6	MiniMax-M3
Released	Aug 12, 2026	Jun 1, 2026
Knowledge cutoff	Feb 1, 2026	Jan 2025
Weights	Closed: hosted access only	Open: downloadable
Developer’s country	United States	China
Hosts selling it	35including xAI directly	56including MiniMax directly
Test results
Capability index	156.4 (best of these models)#21 of 274	146.9#68 of 274
LiveBench overall	78.0% (best of these models)#18 of 66	67.3%#61 of 66
Arena text	1454 (best of these models)#73 of 413	1440#96 of 413
LiveBench coding	76.8% (best of these models)#42 of 66	68.2%#64 of 66
Arena WebDev	1620 (best of these models)#23 of 138	1482#58 of 138
Arena coding	1507 (best of these models)#64 of 408	1494#86 of 408
LiveBench mathematics	92.6% (best of these models)#25 of 66	77.0%#65 of 66
Mock AIME 2024–2025	99.2% (best of these models)#15 of 297	71.1%#133 of 297
FrontierMath Tiers 1–3	66.0%#28 of 114	Not tested
FrontierMath Tier 4	31.7%#33 of 70	Not tested
Arena math	1448 (best of these models)#78 of 396	1432#102 of 396
SimpleQA Verified	49.3%#27 of 86	Not tested
LiveBench agentic coding	57.0% (best of these models)#22 of 66	40.7%#60 of 66
DeepSWE	67.5%#20 of 69	Not tested
CursorBench	41.4%#24 of 62	Not tested
LiveBench language	83.7% (best of these models)#19 of 66	76.8%#45 of 66
LiveBench instructions	71.9% (best of these models)#20 of 66	57.5%#61 of 66
Arena creative writing	1445 (best of these models)#52 of 411	1406#99 of 411
Arena instruction following	1451 (best of these models)#63 of 413	1434#88 of 413
LiveBench data analysis	73.9%#40 of 66	76.2% (best of these models)#34 of 66
LiveBench reasoning	90.5% (best of these models)#12 of 66	74.5%#61 of 66
GPQA Diamond	94.0% (best of these models)#11 of 319	90.9%#34 of 319
Chess puzzles	40.0% (best of these models)#24 of 227	14.0%#113 of 227
Arena hard prompts	1479 (best of these models)#67 of 413	1463#90 of 413
Price per million tokens
Input	$2.00	$0.30 (best of these models)
Output	$6.00	$1.20 (best of these models)
Blended, 3 input to 1 output	$3.00	$0.525 (best of these models)
Cached input	$0.50	$0.06 (best of these models)
Long requests	$4.00 in, $12.00 outabove 200K tokens	$0.60 in, $2.40 outabove 512K tokens
The maker’s own price	This listing	This listing
Limits
Context window	500K tokens	1M tokens (best of these models)
Max input	372K tokens	512K tokens (best of these models)
Max output	500K tokens	512K tokens (best of these models)
Features
Reads	images, PDFs and text	images, text and video
Produces	text	text
Reasoning	Yeseffort low, medium, high, xhigh	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), Datacurve DeepSWE, compiled by 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.