Head-to-head comparison

Gemini 3.6 Flash vs. Grok 4.6

Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.

shared result series: 44
distinct benchmarks: 22
latest retrieval: 2026-09-04

First modelSecond model

Specifications

General specifications

Release date, availability, context window, architecture, and published parameter counts at a glance. Undisclosed details remain marked as unavailable.

Specifications for Gemini 3.6 Flash and Grok 4.6
Attribute	Gemini 3.6 Flash	Grok 4.6
Provider	Google	xAI
Released	Jul 21, 2026	Aug 12, 2026
Availability	Active	Active
Model type	Proprietary	Proprietary
Parameters	Not published	Not published
Architecture	Not published	Not published
Context window	1,048,576 tokens	500,000 tokens
Knowledge cutoff	Not published	February 1, 2026
Technical sources	Model	Model

Pricing

API pricing compared

The table compares official standard API rates per 1M tokens, including published cache pricing. Batch, fast, priority, regional surcharges, tool calls, and cloud platform pricing are excluded.

API pricing for Gemini 3.6 Flash and Grok 4.6
Price type	Gemini 3.6 Flash	Grok 4.6
API input	$0.75	$2 ≤200K / $4 >200K
API output	$3.75	$6 ≤200K / $12 >200K
Cache read	$0.07	$0.5 ≤200K / $1 >200K
Cache write (5 min.)	Not listed	Not listed
Cache write (1 hr.)	Not listed	Not listed
Price verified	08/16/2026 Source	08/16/2026 Source

Gemini 3.6 FlashGrok 4.6

API inputUSD per 1M tokens, base tier

Gemini 3.6 Flash$0.75

Grok 4.6$2

API outputUSD per 1M tokens, base tier

Gemini 3.6 Flash$3.75

Grok 4.6$6

Cache readUSD per 1M tokens, base tier

Gemini 3.6 Flash$0.075

Grok 4.6$0.5

Key to the marks:better valuebetter, but not conclusivetie

Pricing by provider

Direct developer pricing and provider endpoint tariffs routed through OpenRouter are listed separately. Prices are in USD per 1M tokens. Context-dependent direct tiers plus regional, Flex, Priority, and other OpenRouter tariffs remain individually identifiable.

Provider pricing for Gemini 3.6 Flash and Grok 4.6
Model	Provider	Purchase route and tariff	Input per 1M tokens	Output per 1M tokens	Source
Gemini 3.6 Flash	Google	Direct from developerStandard API	$0.75	$3.75	Source08/16/2026
	Google	Via OpenRoutergoogle-vertex/global	$0.75	$3.75	Source09/06/2026
	Google	Via OpenRoutergoogle-vertex/global/flex	Lowest listed price: $0.375	Lowest listed price: $1.875	Source09/06/2026
	Google	Via OpenRoutergoogle-vertex/global/priority	$1.35	$6.75	Source09/06/2026
	Google	Via OpenRoutergoogle-vertex/us	$0.825	$4.125	Source09/06/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio	$0.75	$3.75	Source09/06/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio/flex	Lowest listed price: $0.375	Lowest listed price: $1.875	Source09/06/2026
	Google AI Studio	Via OpenRoutergoogle-ai-studio/priority	$1.35	$6.75	Source09/06/2026
Grok 4.6	xAI	Direct from developerUp to 200,000 context tokens	Lowest listed price: $2	Lowest listed price: $6	Source08/16/2026
	xAI	Direct from developerAbove 200,000 context tokens	$4	$12	Source08/16/2026
	Amazon Bedrock	Via OpenRouteramazon-bedrock/us-west-2	$2.2	$6.6	Source09/06/2026
	xAI	Via OpenRouterxai	Lowest listed price: $2	Lowest listed price: $6	Source09/06/2026
	xAI	Via OpenRouterxai/priority	$4	$12	Source09/06/2026
	xAI	Via OpenRouterxai/zdr	Lowest listed price: $2	Lowest listed price: $6	Source09/06/2026
	xAI	Via OpenRouterxai/zdr/priority	$4	$12	Source09/06/2026

Performance

Shared benchmarks

Only published results with the same benchmark version, task, metric, and comparison cohort are paired. Different reasoning levels, agents, harnesses, or output limits appear directly in the table.

Capability profile from matched benchmarks

Each axis averages directly matched benchmark families. A value of 100 means the stronger value within this pair, not a universal quality score.

Gemini 3.6 Flash

Grok 4.6

Coding: 87.3 / 99.9 (5 benchmark families)

Reasoning: 99.3 / 99.3 (2 benchmark families)

Mathematics: 100 / 96.1 (1 benchmark family)

Knowledge: 99.9 / 99.7 (2 benchmark families)

Finance: 99.3 / 96.7 (6 benchmark families)

Legal: 68.3 / 99.7 (4 benchmark families)

Agentic tasks: 94.3 / 100 (1 benchmark family)

Productivity: 84.6 / 100 (1 benchmark family)

44 matched rows from 22 benchmark families were considered. The radar shows 8 of 12 comparable categories.

Gemini 3.6 FlashGrok 4.6

BioMysteryBenchOverall. Higher is better. No documented setup difference

Gemini 3.6 Flash58.519 %

Grok 4.672.222 %

Code MigrationOverall. Higher is better. No documented setup difference

Gemini 3.6 Flash30.928 %

Grok 4.644.572 %

CorpFin v2Overall. Higher is better. No documented setup difference

Gemini 3.6 Flash63.326 %

Grok 4.666.161 %

EMBOverall. Higher is better. No documented setup difference

Gemini 3.6 Flash65.411 %

Grok 4.662.727 %

Finance Agent (v2)Overall. Higher is better. No documented setup difference

Gemini 3.6 Flash56.296 %

Grok 4.653.682 %

GPQA DiamondOverall. Higher is better. No documented setup difference

Gemini 3.6 Flash93.434 %

Grok 4.694.697 %

Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference

Gemini 3.6 Flash3.333 %

Grok 4.615.833 %

Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference

Gemini 3.6 Flash25 %

Grok 4.648.077 %

LegalBenchOverall. Higher is better. No documented setup difference

Gemini 3.6 Flash86.705 %

Grok 4.686.307 %

LiveCodeBench v6Overall. Higher is better. No documented setup difference

Gemini 3.6 Flash88.08 %

Grok 4.688.224 %

LMArena Text, Style ControlOverall. Higher is better. No documented setup difference

Gemini 3.6 Flash1,480.192

Grok 4.61,461.115

MedCodeOverall. Higher is better. No documented setup difference

Gemini 3.6 Flash53.153 %

Grok 4.644.712 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Gemini 3.6 Flash and Grok 4.6
Benchmark and task	Gemini 3.6 Flash	Grok 4.6	Source
BioMysteryBenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is betterSettings: Harness: Terminus 2	58.519 %	Winner72.222 %	Vals AI Source details Data as of: 09/02/2026
Code MigrationOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	30.928 %	Winner44.572 %	Vals AI Source details Data as of: 09/03/2026
CorpFin v2Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	63.326 %	Winner66.161 %	Vals AI Source details Data as of: 08/12/2026
EMBOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner65.411 %	62.727 %	Vals AI Source details Data as of: 09/03/2026
Finance Agent (v2)Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	Winner56.296 %	53.682 %	Vals AI Source details Data as of: 09/03/2026
GPQA DiamondOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	93.434 %	Winner94.697 %	Vals AI Source details Data as of: 09/01/2026
Harvey's Legal Agent BenchmarkOverall · Task fully resolved Test details No documented difference in the test setupVersion: 1Metric: task resolution rateScoring: Higher is better	3.333 %	Winner15.833 %	Vals AI Source details Data as of: 09/03/2026
Legal Research BenchOverall · All-pass Test details No documented difference in the test setupVersion: 1Metric: all-pass rateScoring: Higher is better	25 %	Winner48.077 %	Vals AI Source details Data as of: 09/03/2026
LegalBenchOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner86.705 %	86.307 %	Vals AI Source details Data as of: 09/01/2026
LiveCodeBench v6Overall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	88.08 %	Winner88.224 %	Vals AI Source details Data as of: 09/01/2026
LMArena Text, Style ControlOverall Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 22,009 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 3,453 anonymous pairwise votes.	Winner1,480.192 95% confidence interval: ±5.12The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,461.115 95% confidence interval: ±10.144The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
MedCodeOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner53.153 %	44.712 %	Vals AI Source details Data as of: 09/03/2026
MedScribeOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	79.661 %	Winner86.534 %	Vals AI Source details Data as of: 09/03/2026
MMLU-ProOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	89.276 %	Winner89.4 %	Vals AI Source details Data as of: 09/01/2026
MortgageTaxOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner67.608 %	64.189 %	Vals AI Source details Data as of: 09/01/2026
Public Benefits Bench v1.1Overall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is better	56.563 %	Winner66.847 %	Vals AI Source details Data as of: 09/01/2026
SAGEOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	Winner48.686 %	28.9 %	Vals AI Source details Data as of: 09/03/2026
SWE-bench VerifiedOverall Test details No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better	79.6 %	Winner95.6 %	Vals AI Source details Data as of: 09/01/2026
TaxEval v2Overall Test details No documented difference in the test setupVersion: 2Metric: accuracyScoring: Higher is better	Winner74.857 %	71.096 %	Vals AI Source details Data as of: 09/01/2026
Terminal-Bench 2.1Overall Test details No documented difference in the test setupVersion: 2.1Metric: accuracyScoring: Higher is better	73.783 %	Winner78.277 %	Vals AI Source details Data as of: 09/03/2026
Vals IndexOverall Test details No documented difference in the test setupVersion: 2Metric: weighted index scoreScoring: Higher is better	55.354 %	Winner59.167 %	Vals AI Source details Data as of: 09/03/2026
Vibe Code Bench v1.1Overall Test details No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is betterSettings: Harness: OpenHands	64.005 %	Winner76.239 %	Vals AI Source details Data as of: 09/03/2026
LMArena Text, Style ControlBusiness, management and finance Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 4,278 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 705 anonymous pairwise votes.	No clear lead1,477.825 95% confidence interval: ±9.689The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,467.318 95% confidence interval: ±22.146The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlChinese Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 1,402 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 291 anonymous pairwise votes.	1,536.451 95% confidence interval: ±16.413The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,538.386 95% confidence interval: ±33.69The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlCoding Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 6,559 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 838 anonymous pairwise votes.	No clear lead1,518.668 95% confidence interval: ±8.064The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,510.751 95% confidence interval: ±20.826The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlCreative writing Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 4,434 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 651 anonymous pairwise votes.	No clear lead1,469.595 95% confidence interval: ±9.906The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,458.096 95% confidence interval: ±23.926The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlEnglish Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 9,496 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 1,434 anonymous pairwise votes.	Winner1,482.21 95% confidence interval: ±6.94The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,459.46 95% confidence interval: ±15.407The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlEntertainment, sports and media Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 5,582 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 777 anonymous pairwise votes.	No clear lead1,460.607 95% confidence interval: ±8.827The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,443.149 95% confidence interval: ±21.821The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlExcluding ties Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 16,444 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 2,522 anonymous pairwise votes.	Winner1,492.097 95% confidence interval: ±6.81The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,465.128 95% confidence interval: ±14.002The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlExpert prompts Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 2,532 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 401 anonymous pairwise votes.	No clear lead1,501.034 95% confidence interval: ±12.147The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,479.844 95% confidence interval: ±28.841The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlHard prompts Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 14,868 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 2,312 anonymous pairwise votes.	No clear lead1,500.579 95% confidence interval: ±6.042The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,484.219 95% confidence interval: ±12.5The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlHard prompts, English Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 6,456 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 927 anonymous pairwise votes.	No clear lead1,496.583 95% confidence interval: ±8.122The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,475.235 95% confidence interval: ±19.394The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlInstruction following Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 7,920 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 1,223 anonymous pairwise votes.	No clear lead1,471.935 95% confidence interval: ±7.562The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,458.276 95% confidence interval: ±17.043The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlLegal and government Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 1,837 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 284 anonymous pairwise votes.	No clear lead1,485.423 95% confidence interval: ±14.207The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,475.664 95% confidence interval: ±33.128The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlLife, physical and social science Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 3,553 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 512 anonymous pairwise votes.	1,491.859 95% confidence interval: ±10.239The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	No clear lead1,492.359 95% confidence interval: ±25.684The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlLonger queries Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 10,520 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 1,609 anonymous pairwise votes.	No clear lead1,486.209 95% confidence interval: ±6.995The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,478.218 95% confidence interval: ±15.132The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlMath Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 1,025 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 216 anonymous pairwise votes.	Winner1,502.939 95% confidence interval: ±18.557The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,426.012 95% confidence interval: ±40.021The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlMathematical professions Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 1,231 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 212 anonymous pairwise votes.	No clear lead1,496.352 95% confidence interval: ±17.313The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,456.037 95% confidence interval: ±39.211The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlMedicine and healthcare Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 1,591 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 225 anonymous pairwise votes.	No clear lead1,482.248 95% confidence interval: ±15.566The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,460.477 95% confidence interval: ±37.871The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlMulti-turn Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 3,653 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 569 anonymous pairwise votes.	Winner1,487.377 95% confidence interval: ±10.437The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,446.12 95% confidence interval: ±25.079The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlNon-English Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 12,513 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 2,019 anonymous pairwise votes.	No clear lead1,472.225 95% confidence interval: ±6.307The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,456.123 95% confidence interval: ±13.128The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlRussian Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 2,307 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 413 anonymous pairwise votes.	Winner1,488.651 95% confidence interval: ±12.806The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,446.297 95% confidence interval: ±28.9The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlSoftware and IT services Test details No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 9,056 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 1,379 anonymous pairwise votes.	No clear lead1,510.253 95% confidence interval: ±7.072The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,503.685 95% confidence interval: ±16.15The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
LMArena Text, Style ControlWriting, literature and language Test details No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.6 Flash: Snapshot: gemini-3.6-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.6 Flash: Style-controlled Arena rating from 5,835 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 921 anonymous pairwise votes.	Winner1,476.996 95% confidence interval: ±8.651The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	1,445.223 95% confidence interval: ±19.746The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.	LMArena Source details Data as of: 09/01/2026
Key to the marks:better valuebetter, but not conclusivetie

How to read this comparison

Winning one benchmark is not an overall verdict

Your workload, budget, and required context length matter most. A coding benchmark says little about visual understanding or agent performance.

The standard price table uses direct developer rates. The provider comparison labels OpenRouter endpoints, regions, and special tariffs separately.

Every result links to its measurement source and retrieval date. Labels distinguish vendor reports, official benchmark leaderboards, and independent evaluations. Disputed or archived results are excluded.

More matchups

Compare Gemini 3.6 Flash and Grok 4.6 with other leading models using the same data and benchmark logic.

View the complete LLM comparison