Gemini 4 Argon vs Grok 4.6

At a glance

• Capability index

  • Gemini 4 Argon164.6
  • Grok 4.6156.3

  Gemini 4 Argon is 8.3 points higher.

• Price per 1M tokens

  • Gemini 4 Argon$4.00
  • Grok 4.6$3.00

  Grok 4.6 is 25% cheaper.

• Context window

  • Gemini 4 Argon1M tokens
  • Grok 4.6500K tokens

  Gemini 4 Argon takes in 2.1 times as much.

• Released

  • Gemini 4 ArgonOct 13, 2026
  • Grok 4.6Aug 12, 2026

  Gemini 4 Argon is 2 months newer.

Where each scores higher

On the 14 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.

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

Everything side by side

Comparison of Gemini 4 Argon vs Grok 4.6

Measure	Gemini 4 ArgonGoogle	Grok 4.6xAI
Model
Maker	Google	xAI
Sold here by	Google	xAI
API model ID	gemini-4-argon	grok-4.6
Released	Oct 13, 2026	Aug 12, 2026
Knowledge cutoff	Mar 2026	Feb 1, 2026
Weights	Closed: hosted access only	Closed: hosted access only
Developer’s country	United States	United States
Hosts selling it	24including Google directly	37including xAI directly
Test results
Capability index	164.6 (best of these models)#5 of 277	156.3#27 of 277
Arena text	1525 (best of these models)#1 of 415	1455#70 of 415
LiveBench overall	Not tested	78.0%#19 of 70
Arena WebDev	1678 (best of these models)#9 of 142	1617#25 of 142
Arena coding	1561 (best of these models)#1 of 410	1510#60 of 410
LiveBench coding	Not tested	76.8%#45 of 70
Mock AIME 2024–2025	100.0% (best of these models)#1 of 303	99.2%#17 of 303
FrontierMath Tiers 1–3	86.0% (best of these models)#10 of 117	66.0%#31 of 117
FrontierMath Tier 4	78.0% (best of these models)#15 of 73	31.7%#35 of 73
Arena math	1529 (best of these models)#1 of 400	1447#83 of 400
LiveBench mathematics	Not tested	92.6%#28 of 70
SimpleQA Verified	76.0% (best of these models)#1 of 90	49.3%#28 of 90
CursorBench	52.9% (best of these models)#6 of 71	41.4%#31 of 71
LiveBench agentic coding	Not tested	57.0%#25 of 70
DeepSWE	Not tested	67.5%#20 of 69
Arena creative writing	1516 (best of these models)#2 of 413	1443#55 of 413
Arena instruction following	1528 (best of these models)#1 of 415	1452#63 of 415
LiveBench language	Not tested	83.7%#19 of 70
LiveBench instructions	Not tested	71.9%#21 of 70
LiveBench data analysis	Not tested	73.9%#42 of 70
GPQA Diamond	96.4% (best of these models)#1 of 323	94.0%#12 of 323
Chess puzzles	59.0% (best of these models)#9 of 243	33.0%#63 of 243
Arena hard prompts	1550 (best of these models)#1 of 415	1481#64 of 415
LiveBench reasoning	Not tested	90.5%#13 of 70
Price per million tokens
Input	$2.00	$2.00
Output	$10.00	$6.00 (best of these models)
Blended, 3 input to 1 output	$4.00	$3.00 (best of these models)
Cached input	$0.10 (best of these models)	$0.50
Audio input	$2.00	Not reported
Long requests	No separate price reported	$4.00 in, $12.00 outabove 200K tokens
The maker’s own price	This listing	This listing
Limits
Context window	1M tokens (best of these models)	500K tokens
Max input	1M tokens (best of these models)	372K tokens
Max output	32.8K tokens	500K tokens (best of these models)
Features
Reads	audio, images, PDFs, text and video	images, PDFs and text
Produces	text	text
Reasoning	Yeseffort low, medium, high	Yeseffort low, medium, high, xhigh
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.