Skip to main content

Head-to-head comparison

Gemini 3.1 Pro Preview 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

Change model selection

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 3.1 Pro Preview and Grok 4.6
AttributeGemini 3.1 Pro PreviewGrok 4.6
ProviderGooglexAI
ReleasedFeb 19, 2026Aug 12, 2026
AvailabilityPreviewActive
Model typeProprietaryProprietary
ParametersNot publishedNot published
ArchitectureNot publishedNot published
Context window1,048,576 tokens500,000 tokens
Knowledge cutoffNot publishedFebruary 1, 2026
Technical sourcesModelModel

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 3.1 Pro Preview and Grok 4.6
Price typeGemini 3.1 Pro PreviewGrok 4.6
API input$2 ≤200K / $4 >200K$2 ≤200K / $4 >200K
API output$12 ≤200K / $18 >200K$6 ≤200K / $12 >200K
Cache read$0.2 ≤200K / $0.4 >200K$0.5 ≤200K / $1 >200K
Cache write (5 min.)Not listedNot listed
Cache write (1 hr.)Not listedNot listed
Price verified07/30/2026 Source08/16/2026 Source
Gemini 3.1 Pro PreviewGrok 4.6
API inputUSD per 1M tokens, base tier
Gemini 3.1 Pro PreviewTie$2
Grok 4.6Tie$2
API outputUSD per 1M tokens, base tier
Gemini 3.1 Pro Preview$12
Grok 4.6Lower price$6
Cache readUSD per 1M tokens, base tier
Gemini 3.1 Pro PreviewLower price$0.2
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 3.1 Pro Preview and Grok 4.6
ModelProviderPurchase route and tariffInput per 1M tokensOutput per 1M tokensSource
Gemini 3.1 Pro PreviewGoogleDirect from developerUp to 200,000 context tokens$2$12Source07/30/2026
GoogleDirect from developerAbove 200,000 context tokens$4$18Source07/30/2026
GoogleVia OpenRoutergoogle-vertex/global$2$12Source09/08/2026
GoogleVia OpenRoutergoogle-vertex/global/flexLowest listed price: $1Lowest listed price: $6Source09/08/2026
GoogleVia OpenRoutergoogle-vertex/global/priority$3.6$21.6Source09/08/2026
Google AI StudioVia OpenRoutergoogle-ai-studio$2$12Source09/08/2026
Google AI StudioVia OpenRoutergoogle-ai-studio/flexLowest listed price: $1Lowest listed price: $6Source09/08/2026
Google AI StudioVia OpenRoutergoogle-ai-studio/priority$3.6$21.6Source09/08/2026
Grok 4.6xAIDirect from developerUp to 200,000 context tokensLowest listed price: $2Lowest listed price: $6Source08/16/2026
xAIDirect from developerAbove 200,000 context tokens$4$12Source08/16/2026
Amazon BedrockVia OpenRouteramazon-bedrock/us-west-2$2.2$6.6Source09/08/2026
xAIVia OpenRouterxaiLowest listed price: $2Lowest listed price: $6Source09/08/2026
xAIVia OpenRouterxai/priority$4$12Source09/08/2026
xAIVia OpenRouterxai/zdrLowest listed price: $2Lowest listed price: $6Source09/08/2026
xAIVia OpenRouterxai/zdr/priority$4$12Source09/08/2026

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.

255075100CodingReasoningMathematicsKnowledgeFinanceLegalAgentic tasksProductivity
Gemini 3.1 Pro Preview
Grok 4.6
Coding: 65.8 / 99.9 (4 benchmark families)
Reasoning: 100 / 99.2 (1 benchmark family)
Mathematics: 51 / 100 (1 benchmark family)
Knowledge: 100 / 98.3 (1 benchmark family)
Finance: 92.3 / 98 (5 benchmark families)
Legal: 47.7 / 99.6 (3 benchmark families)
Agentic tasks: 90.4 / 100 (1 benchmark family)
Productivity: 80.5 / 100 (1 benchmark family)

21 matched rows from 21 benchmark families were considered. The radar shows 8 of 11 comparable categories.

Gemini 3.1 Pro PreviewGrok 4.6
Code MigrationOverall. Higher is better. No documented setup difference
Gemini 3.1 Pro Preview17.313 %
Grok 4.6Winner44.572 %
CorpFin v2Overall. Higher is better. No documented setup difference
Gemini 3.1 Pro Preview64.491 %
Grok 4.6Winner66.161 %
EMBOverall. Higher is better. No documented setup difference
Gemini 3.1 Pro Preview52.616 %
Grok 4.6Winner62.727 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
Gemini 3.1 Pro Preview42.982 %
Grok 4.6Winner53.682 %
GPQA DiamondOverall. Higher is better. No documented setup difference
Gemini 3.1 Pro PreviewWinner95.454 %
Grok 4.694.697 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
Gemini 3.1 Pro Preview0 %
Grok 4.6Winner15.833 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
Gemini 3.1 Pro Preview20.673 %
Grok 4.6Winner48.077 %
LegalBenchOverall. Higher is better. No documented setup difference
Gemini 3.1 Pro PreviewWinner87.398 %
Grok 4.686.307 %
LiveCodeBench v6Overall. Higher is better. No documented setup difference
Gemini 3.1 Pro PreviewWinner88.485 %
Grok 4.688.224 %
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
Gemini 3.1 Pro PreviewHigher measured value1,486.746
Grok 4.61,461.115
MedCodeOverall. Higher is better. No documented setup difference
Gemini 3.1 Pro PreviewWinner59.062 %
Grok 4.644.712 %
MedScribeOverall. Higher is better. No documented setup difference
Gemini 3.1 Pro Preview76.114 %
Grok 4.6Winner86.534 %

Key to the marks:better valuebetter, but not conclusivetie

Benchmark scores for Gemini 3.1 Pro Preview and Grok 4.6
Benchmark and taskGemini 3.1 Pro PreviewGrok 4.6Source
Code MigrationOverall
Test details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
17.313 %
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
64.491 %
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
52.616 %
Winner62.727 %
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
42.982 %
Winner53.682 %
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
Winner95.454 %
94.697 %
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
0 %
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
20.673 %
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
Winner87.398 %
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
Winner88.485 %
88.224 %
Vals AI
Source details
Data as of: 09/01/2026
LMArena Text, Style ControlOverall
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 102,763 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 3,453 anonymous pairwise votes.
Higher measured value1,486.746
95% confidence interval: ±3.217The 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
Winner59.062 %
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
76.114 %
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
Winner90.987 %
89.4 %
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
Winner69.396 %
64.189 %
Vals AI
Source details
Data as of: 09/01/2026
ProofBenchOverall
Test details
No documented difference in the test setupVersion: 1.1Metric: accuracyScoring: Higher is better
26 %
Winner51 %
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
53.789 %
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
Winner48.677 %
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
78.8 %
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
Winner72.882 %
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
70.787 %
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
41.903 %
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
32.034 %
Winner76.239 %
Vals AI
Source details
Data as of: 09/03/2026
LMArena Text, Style ControlBusiness, management and finance
Test details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 20,283 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 705 anonymous pairwise votes.
Higher measured value1,476.52
95% confidence interval: ±5.472The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 6,195 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 291 anonymous pairwise votes.
1,530.803
95% confidence interval: ±8.555The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Higher measured value1,538.386
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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 28,421 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 838 anonymous pairwise votes.
Higher measured value1,521.238
95% confidence interval: ±4.96The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 17,931 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 651 anonymous pairwise votes.
Higher measured value1,479.063
95% confidence interval: ±5.907The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 46,126 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 1,434 anonymous pairwise votes.
Higher measured value1,488.416
95% confidence interval: ±4.243The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 22,824 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 777 anonymous pairwise votes.
Higher measured value1,466.085
95% confidence interval: ±5.435The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 77,271 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 2,522 anonymous pairwise votes.
Higher measured value1,500.846
95% confidence interval: ±4.346The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 10,205 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 401 anonymous pairwise votes.
Higher measured value1,508.867
95% confidence interval: ±6.993The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 66,600 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 2,312 anonymous pairwise votes.
Higher measured value1,507.024
95% confidence interval: ±3.905The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 30,707 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 927 anonymous pairwise votes.
Higher measured value1,505.54
95% confidence interval: ±4.906The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 34,679 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 1,223 anonymous pairwise votes.
Higher measured value1,480.715
95% confidence interval: ±4.654The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 8,416 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 284 anonymous pairwise votes.
Higher measured value1,496.16
95% confidence interval: ±7.523The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 17,014 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 512 anonymous pairwise votes.
Higher measured value1,511.7
95% confidence interval: ±5.722The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,492.359
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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 44,135 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 1,609 anonymous pairwise votes.
Higher measured value1,499.421
95% confidence interval: ±4.563The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 5,400 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 216 anonymous pairwise votes.
Higher measured value1,488.603
95% confidence interval: ±8.751The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 5,553 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 212 anonymous pairwise votes.
Higher measured value1,484.657
95% confidence interval: ±8.955The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 7,650 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 225 anonymous pairwise votes.
Higher measured value1,502.411
95% confidence interval: ±7.878The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 17,803 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 569 anonymous pairwise votes.
Higher measured value1,494.475
95% confidence interval: ±5.726The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 56,633 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 2,019 anonymous pairwise votes.
Higher measured value1,479.804
95% confidence interval: ±3.961The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 11,004 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 413 anonymous pairwise votes.
Higher measured value1,499.732
95% confidence interval: ±6.696The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 40,558 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 1,379 anonymous pairwise votes.
Higher measured value1,511.753
95% confidence interval: ±4.414The 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
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.1 Pro Preview: Snapshot: gemini-3.1-pro-preview, Harness: Arena text, style control
Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style control
Gemini 3.1 Pro Preview: Style-controlled Arena rating from 25,434 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 921 anonymous pairwise votes.
Higher measured value1,480.011
95% confidence interval: ±5.156The 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

Our model tests

Community tests you can inspect

Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.

Pelican on a bicycle

A community classic for free-form SVG drawing.

Gemini 3.1 Pro Preview

API access was unavailable for this run. The model was not evaluated.

First attempt
Run date
7 Sept 2026
API provider
openrouter
Requested API model
google/gemini-3.1-pro-preview
Pinned endpoint
Google AI Studio | google/gemini-3.1-pro-preview-20260219
Reasoning setting
high
Temperature
Provider default
Token limit including reasoning
8,192 tokens
Test protocol
community-visual-tests-v1
Technical checks
Not run

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Grok 4.6

API access was unavailable for this run. The model was not evaluated.

First attempt
Run date
7 Sept 2026
API provider
openrouter
Requested API model
x-ai/grok-4.6
Pinned endpoint
xAI | x-ai/grok-4.6-20260810
Reasoning setting
high
Temperature
Provider default
Token limit including reasoning
8,192 tokens
Test protocol
community-visual-tests-v1
Technical checks
Not run

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Prompt and test conditions

Generate an SVG of a pelican riding a bicycle

Token limit including reasoning: 8,192 tokens

Task origin (Simon Willison)

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 3.1 Pro Preview and Grok 4.6 with other leading models using the same data and benchmark logic.

View the complete LLM comparison