Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
shared result series
68
distinct benchmarks
23
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.
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.
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 3.5 Flash and Grok 4.6
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 3.5 Flash
Grok 4.6
Coding: 81.1 / 100 (5 benchmark families)
Reasoning: 98.9 / 99.5 (2 benchmark families)
Mathematics: 80.4 / 98.2 (2 benchmark families)
Knowledge: 100 / 99.8 (2 benchmark families)
Finance: 99.6 / 96.9 (6 benchmark families)
Legal: 69.1 / 100 (4 benchmark families)
Agentic tasks: 94.7 / 100 (2 benchmark families)
Productivity: 89 / 100 (1 benchmark family)
45 matched rows from 23 benchmark families were considered. The radar shows 8 of 12 comparable categories.
Gemini 3.5 FlashGrok 4.6
Code MigrationOverall. Higher is better. No documented setup difference
Gemini 3.5 Flash26.745 %
Grok 4.6Winner44.572 %
CorpFin v2Overall. Higher is better. No documented setup difference
Gemini 3.5 Flash64.686 %
Grok 4.6Winner66.161 %
EMBOverall. Higher is better. No documented setup difference
Gemini 3.5 FlashWinner63.548 %
Grok 4.662.727 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
Gemini 3.5 FlashWinner57.861 %
Grok 4.653.682 %
GPQA DiamondOverall. Higher is better. No documented setup difference
Gemini 3.5 Flash92.676 %
Grok 4.6Winner94.697 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
Gemini 3.5 Flash2.5 %
Grok 4.6Winner15.833 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
Gemini 3.5 Flash30.769 %
Grok 4.6Winner48.077 %
LegalBenchOverall. Higher is better. No documented setup difference
Gemini 3.5 Flash83.602 %
Grok 4.6Winner86.307 %
LiveCodeBench v6Overall. Higher is better. No documented setup difference
Gemini 3.5 Flash87.604 %
Grok 4.6Winner88.224 %
LMArena Text, Style ControlOverall. Higher is better. No documented setup difference
Gemini 3.5 FlashWinner1,479.148
Grok 4.61,461.115
MedCodeOverall. Higher is better. No documented setup difference
Gemini 3.5 FlashWinner55.825 %
Grok 4.644.712 %
MedScribeOverall. Higher is better. No documented setup difference
Gemini 3.5 Flash76.574 %
Grok 4.6Winner86.534 %
Key to the marks:better valuebetter, but not conclusivetie
Benchmark scores for Gemini 3.5 Flash and Grok 4.6
Benchmark and task
Gemini 3.5 Flash
Grok 4.6
Source
Code MigrationOverallTest details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 33,874 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 3,453 anonymous pairwise votes.
Winner1,479.148
95% confidence interval: ±4.345The 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.
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 32,274 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 3,453 anonymous pairwise votes.
Higher measured value1,474.438
95% confidence interval: ±4.676The 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 Text, Style ControlBusiness, management and financeTest details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 6,750 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 705 anonymous pairwise votes.
1,465.666
95% confidence interval: ±7.938The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
No clear lead1,467.318
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 Text, Style ControlBusiness, management and financeTest details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 6,429 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 705 anonymous pairwise votes.
1,460.515
95% confidence interval: ±8.197The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Higher measured value1,467.318
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.
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 2,185 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 291 anonymous pairwise votes.
1,523.785
95% confidence interval: ±13.691The 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.
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 1,995 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 291 anonymous pairwise votes.
1,511.537
95% confidence interval: ±14.076The 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.
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 9,858 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 838 anonymous pairwise votes.
1,507.896
95% confidence interval: ±6.918The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
No clear lead1,510.751
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.
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 9,502 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 838 anonymous pairwise votes.
1,503.02
95% confidence interval: ±7.086The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Higher measured value1,510.751
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.
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 6,261 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 651 anonymous pairwise votes.
No clear lead1,464.209
95% confidence interval: ±8.449The 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.
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 6,181 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 651 anonymous pairwise votes.
Higher measured value1,466.381
95% confidence interval: ±8.668The 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.
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 14,760 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 1,434 anonymous pairwise votes.
No clear lead1,477.601
95% confidence interval: ±5.811The 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.
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 13,969 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 1,434 anonymous pairwise votes.
Higher measured value1,477.927
95% confidence interval: ±6.021The 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 Text, Style ControlEntertainment, sports and mediaTest details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 8,008 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 777 anonymous pairwise votes.
No clear lead1,455.503
95% confidence interval: ±7.604The 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 Text, Style ControlEntertainment, sports and mediaTest details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 8,080 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 777 anonymous pairwise votes.
Higher measured value1,453.176
95% confidence interval: ±7.743The 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.
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 25,685 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 2,522 anonymous pairwise votes.
Winner1,489.285
95% confidence interval: ±5.708The 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.
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 24,291 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 2,522 anonymous pairwise votes.
Higher measured value1,484.217
95% confidence interval: ±6.104The 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.
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 3,765 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 401 anonymous pairwise votes.
No clear lead1,491.166
95% confidence interval: ±10.263The 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.
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 3,630 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 401 anonymous pairwise votes.
Higher measured value1,486.377
95% confidence interval: ±10.426The 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.
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 22,707 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 2,312 anonymous pairwise votes.
No clear lead1,497.725
95% confidence interval: ±5.13The 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.
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 21,743 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 2,312 anonymous pairwise votes.
Higher measured value1,492.408
95% confidence interval: ±5.431The 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.
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 9,989 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 927 anonymous pairwise votes.
No clear lead1,491.638
95% confidence interval: ±6.84The 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.
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 9,430 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 927 anonymous pairwise votes.
Higher measured value1,489.936
95% confidence interval: ±7.027The 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.
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 12,015 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 1,223 anonymous pairwise votes.
No clear lead1,466.61
95% confidence interval: ±6.374The 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.
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 11,631 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 1,223 anonymous pairwise votes.
Higher measured value1,463.044
95% confidence interval: ±6.57The 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 Text, Style ControlLegal and governmentTest details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 2,816 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 284 anonymous pairwise votes.
1,473.514
95% confidence interval: ±11.897The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
No clear lead1,475.664
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 Text, Style ControlLegal and governmentTest details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 2,606 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 284 anonymous pairwise votes.
Higher measured value1,485.22
95% confidence interval: ±12.369The 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 Text, Style ControlLife, physical and social scienceTest details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 5,533 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 512 anonymous pairwise votes.
1,488.436
95% confidence interval: ±8.49The 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 Text, Style ControlLife, physical and social scienceTest details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 5,219 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 512 anonymous pairwise votes.
Higher measured value1,492.855
95% confidence interval: ±8.828The 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.
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 15,749 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 1,609 anonymous pairwise votes.
No clear lead1,482.425
95% confidence interval: ±6.06The 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.
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 15,472 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 1,609 anonymous pairwise votes.
1,476.768
95% confidence interval: ±6.209The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Higher measured value1,478.218
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.
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 1,638 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 216 anonymous pairwise votes.
Winner1,504.032
95% confidence interval: ±14.9The 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.
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 1,466 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 216 anonymous pairwise votes.
Higher measured value1,477.944
95% confidence interval: ±15.611The 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.
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 1,911 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 212 anonymous pairwise votes.
No clear lead1,485.634
95% confidence interval: ±14.143The 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.
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 1,705 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 212 anonymous pairwise votes.
Higher measured value1,483.603
95% confidence interval: ±14.956The 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 Text, Style ControlMedicine and healthcareTest details
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 2,508 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 225 anonymous pairwise votes.
No clear lead1,492.702
95% confidence interval: ±12.721The 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 Text, Style ControlMedicine and healthcareTest details
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 2,358 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 225 anonymous pairwise votes.
Higher measured value1,481.624
95% confidence interval: ±13.127The 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.
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 5,775 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 569 anonymous pairwise votes.
Winner1,485.062
95% confidence interval: ±8.535The 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.
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 5,415 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 569 anonymous pairwise votes.
Higher measured value1,476.95
95% confidence interval: ±8.834The 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.
No documented difference in the test setupNo clear leadVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 19,113 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 2,019 anonymous pairwise votes.
No clear lead1,472.208
95% confidence interval: ±5.341The 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.
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 18,303 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 2,019 anonymous pairwise votes.
Higher measured value1,465.266
95% confidence interval: ±5.602The 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.
No documented difference in the test setupVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-high, Reasoning: high, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 3,509 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 413 anonymous pairwise votes.
Winner1,490.286
95% confidence interval: ±10.554The 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.
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGemini 3.5 Flash: Snapshot: gemini-3.5-flash-medium, Reasoning: medium, Harness: Arena text, style control Grok 4.6: Snapshot: grok-4.6-high, Reasoning: high, Harness: Arena text, style controlGemini 3.5 Flash: Style-controlled Arena rating from 3,399 anonymous pairwise votes.Grok 4.6: Style-controlled Arena rating from 413 anonymous pairwise votes.
Higher measured value1,490.675
95% confidence interval: ±10.793The 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.
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 3.5 Flash
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-3.5-flash
Pinned endpoint
Google AI Studio | google/gemini-3.5-flash-20260519
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.
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
Related LLM comparisons
Compare Gemini 3.5 Flash and Grok 4.6 with other leading models using the same data and benchmark logic.