Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
shared result series
95
distinct benchmarks
5
latest retrieval
2026-10-15
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.
No provider tariff for Muse Wonder is available in the stored OpenRouter snapshot. The official direct price is still shown.
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.
Not enough directly matched categories for a reliable radar
Only 0 of at least 5 categories have comparable, direct model measurements. The benchmark tables below show the available evidence without filling missing axes.
GPT-5.4Muse Wonder
Code MigrationOverall. Higher is better. Test setup not documented as identical
GPT-5.434.984 %
Muse WonderHigher measured value62.552 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. Test setup not documented as identical
GPT-5.40 %
Muse WonderHigher measured value17.083 %
LMArena Code Arena WebDevOverall. Higher is better. Test setup not documented as identical
GPT-5.41,401.766
Muse WonderHigher measured value1,650.947
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
GPT-5.41,464.728
Muse WonderHigher measured value1,512.671
Vibe Code Bench v1.1Overall. Higher is better. Test setup not documented as identical
GPT-5.467.421 %
Muse WonderHigher measured value83.089 %
Code MigrationCLI. Higher is better. Test setup not documented as identical
GPT-5.423.788 %
Muse WonderHigher measured value60.07 %
Harvey's Legal Agent BenchmarkAntitrust Competition · Criteria passed. Higher is better. Test setup not documented as identical
GPT-5.476.449 %
Muse WonderHigher measured value93.841 %
LMArena Code Arena WebDevWebdev. Higher is better. Test setup not documented as identical
GPT-5.41,401.766
Muse WonderHigher measured value1,650.947
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
GPT-5.41,475.066
Muse WonderHigher measured value1,512.671
Code MigrationCOBOL. Higher is better. Test setup not documented as identical
GPT-5.468.571 %
Muse WonderHigher measured value70 %
Harvey's Legal Agent BenchmarkAntitrust Competition · Task fully resolved. Higher is better. Test setup not documented as identical
GPT-5.40 %
Muse WonderHigher measured value20 %
LMArena Code Arena WebDevWebdev-html. Higher is better. Test setup not documented as identical
GPT-5.41,434.816
Muse WonderHigher measured value1,721.908
Key to the marks:better valuebetter, but not conclusivetie
Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Code Arena WebDev Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Code Arena WebDevGPT-5.4: Arena rating from 3,990 published pairwise votes.Muse Wonder: Arena rating from 1,228 published pairwise votes.
1,401.766
95% confidence interval: ±10.455The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,650.947
95% confidence interval: ±18.263The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 67,880 published pairwise votes.Muse Wonder: Arena rating from 1,944 published pairwise votes.
1,464.728
95% confidence interval: ±3.69The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,512.671
95% confidence interval: ±13.236The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Code Arena WebDev Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Code Arena WebDevGPT-5.4: Arena rating from 3,990 published pairwise votes.Muse Wonder: Arena rating from 1,228 published pairwise votes.
1,401.766
95% confidence interval: ±10.455The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,650.947
95% confidence interval: ±18.263The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 64,787 published pairwise votes.Muse Wonder: Arena rating from 1,944 published pairwise votes.
1,475.066
95% confidence interval: ±3.765The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,512.671
95% confidence interval: ±13.236The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Code Arena WebDev Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Code Arena WebDevGPT-5.4: Arena rating from 528 published pairwise votes.Muse Wonder: Arena rating from 158 published pairwise votes.
1,434.816
95% confidence interval: ±27.294The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,721.908
95% confidence interval: ±51.47The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 13,848 published pairwise votes.Muse Wonder: Arena rating from 338 published pairwise votes.
1,473.882
95% confidence interval: ±6.361The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,500.247
95% confidence interval: ±30.856The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Test setup not documented as identicalNo direct winnerVersion: webdevMetric: WebDev Arena Bradley-Terry ratingScoring: Higher is betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Code Arena WebDev Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Code Arena WebDevGPT-5.4: Arena rating from 2,727 published pairwise votes.Muse Wonder: Arena rating from 787 published pairwise votes.
1,391.351
95% confidence interval: ±12.752The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,637.813
95% confidence interval: ±23.199The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 13,095 published pairwise votes.Muse Wonder: Arena rating from 338 published pairwise votes.
1,481.483
95% confidence interval: ±6.462The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,500.247
95% confidence interval: ±30.856The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 18,933 published pairwise votes.Muse Wonder: Arena rating from 487 published pairwise votes.
1,511.592
95% confidence interval: ±5.788The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,557.956
95% confidence interval: ±26.189The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 17,605 published pairwise votes.Muse Wonder: Arena rating from 487 published pairwise votes.
1,520.364
95% confidence interval: ±5.837The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,557.956
95% confidence interval: ±26.189The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 11,357 published pairwise votes.Muse Wonder: Arena rating from 427 published pairwise votes.
1,434.365
95% confidence interval: ±6.8The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,485.682
95% confidence interval: ±29.474The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 11,142 published pairwise votes.Muse Wonder: Arena rating from 427 published pairwise votes.
1,442.006
95% confidence interval: ±6.936The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,485.682
95% confidence interval: ±29.474The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 30,866 published pairwise votes.Muse Wonder: Arena rating from 802 published pairwise votes.
1,468.033
95% confidence interval: ±4.897The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,523.395
95% confidence interval: ±20.831The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 29,345 published pairwise votes.Muse Wonder: Arena rating from 802 published pairwise votes.
1,476.182
95% confidence interval: ±4.944The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,523.395
95% confidence interval: ±20.831The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 14,807 published pairwise votes.Muse Wonder: Arena rating from 536 published pairwise votes.
1,431.662
95% confidence interval: ±6.25The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,468.099
95% confidence interval: ±25.703The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 14,168 published pairwise votes.Muse Wonder: Arena rating from 536 published pairwise votes.
1,440.873
95% confidence interval: ±6.398The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,468.099
95% confidence interval: ±25.703The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 52,190 published pairwise votes.Muse Wonder: Arena rating from 1,390 published pairwise votes.
1,470.709
95% confidence interval: ±4.819The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,538.781
95% confidence interval: ±18.91The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 49,666 published pairwise votes.Muse Wonder: Arena rating from 1,390 published pairwise votes.
1,484.209
95% confidence interval: ±4.916The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,538.781
95% confidence interval: ±18.91The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 6,735 published pairwise votes.Muse Wonder: Arena rating from 212 published pairwise votes.
1,491.618
95% confidence interval: ±8.214The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,512.579
95% confidence interval: ±38.177The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 6,353 published pairwise votes.Muse Wonder: Arena rating from 212 published pairwise votes.
Higher measured value1,514.397
95% confidence interval: ±8.348The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
1,512.579
95% confidence interval: ±38.177The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 44,750 published pairwise votes.Muse Wonder: Arena rating from 1,218 published pairwise votes.
1,486.787
95% confidence interval: ±4.46The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,533.453
95% confidence interval: ±16.637The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 42,150 published pairwise votes.Muse Wonder: Arena rating from 1,218 published pairwise votes.
1,496.34
95% confidence interval: ±4.508The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,533.453
95% confidence interval: ±16.637The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 21,088 published pairwise votes.Muse Wonder: Arena rating from 527 published pairwise votes.
1,486.355
95% confidence interval: ±5.603The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,524.593
95% confidence interval: ±25.568The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 19,731 published pairwise votes.Muse Wonder: Arena rating from 527 published pairwise votes.
1,492.959
95% confidence interval: ±5.666The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,524.593
95% confidence interval: ±25.568The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 23,401 published pairwise votes.Muse Wonder: Arena rating from 653 published pairwise votes.
1,460.371
95% confidence interval: ±5.375The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,502.929
95% confidence interval: ±22.755The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 21,888 published pairwise votes.Muse Wonder: Arena rating from 653 published pairwise votes.
1,470.847
95% confidence interval: ±5.456The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,502.929
95% confidence interval: ±22.755The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 11,092 published pairwise votes.Muse Wonder: Arena rating from 285 published pairwise votes.
1,477.818
95% confidence interval: ±6.708The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,527.653
95% confidence interval: ±35.27The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 10,648 published pairwise votes.Muse Wonder: Arena rating from 285 published pairwise votes.
1,487.525
95% confidence interval: ±6.826The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,527.653
95% confidence interval: ±35.27The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 29,953 published pairwise votes.Muse Wonder: Arena rating from 866 published pairwise votes.
1,477.265
95% confidence interval: ±5.203The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,504.143
95% confidence interval: ±19.981The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4-high, Reasoning: high, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 28,449 published pairwise votes.Muse Wonder: Arena rating from 866 published pairwise votes.
1,480.812
95% confidence interval: ±5.275The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,504.143
95% confidence interval: ±19.981The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, 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 betterGPT-5.4: Snapshot: gpt-5.4, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.4: Arena rating from 12,653 published pairwise votes.Muse Wonder: Arena rating from 256 published pairwise votes.
1,479.954
95% confidence interval: ±6.559The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
Higher measured value1,544.436
95% confidence interval: ±35.53The Arena score measures human preference rather than a fixed capability test. The confidence interval, Arena category, and model configuration are part of the result.
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 GPT-5.4 and Muse Wonder with other leading models using the same data and benchmark logic.
