Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
shared result series
163
distinct benchmarks
18
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-5.6 LunaMuse Wonder
BioMysteryBenchOverall. Higher is better. Test setup not documented as identical
GPT-5.6 Luna61.481 %
Muse WonderHigher measured value67.037 %
Code MigrationOverall. Higher is better. Test setup not documented as identical
GPT-5.6 Luna44.55 %
Muse WonderHigher measured value62.552 %
CyberBench v1.1Overall. Higher is better. Test setup not documented as identical
GPT-5.6 Luna73.631 %
Muse WonderHigher measured value80.357 %
EMBOverall. Higher is better. Test setup not documented as identical
GPT-5.6 LunaHigher measured value67.116 %
Muse Wonder67.084 %
Finance Agent (v2)Overall. Higher is better. Test setup not documented as identical
GPT-5.6 Luna55.044 %
Muse WonderHigher measured value56.637 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. Test setup not documented as identical
GPT-5.6 Luna1.25 %
Muse WonderHigher measured value17.083 %
IOIOverall. Higher is better. Test setup not documented as identical
GPT-5.6 Luna61.778 %
Muse WonderHigher measured value66.944 %
Legal Research BenchOverall · All-pass. Higher is better. Test setup not documented as identical
GPT-5.6 Luna36.538 %
Muse WonderHigher measured value50.481 %
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
GPT-5.6 Luna1,452.509
Muse WonderHigher measured value1,512.671
MysteryMechanismOverall. Higher is better. Test setup not documented as identical
GPT-5.6 Luna14.414 %
Muse WonderHigher measured value27.477 %
ProofBenchOverall. Higher is better. Test setup not documented as identical
GPT-5.6 Luna60 %
Muse WonderHigher measured value84 %
Public Benefits Bench v1.1Overall. Higher is better. Test setup not documented as identical
GPT-5.6 Luna61.164 %
Muse WonderHigher measured value70.23 %
Key to the marks:better valuebetter, but not conclusivetie
Test setup not documented as identicalNo direct winnerVersion: style-control-v1Metric: style-controlled Bradley-Terry ratingScoring: Higher is betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.6 Luna: Arena rating from 41,103 published pairwise votes.Muse Wonder: Arena rating from 1,944 published pairwise votes.
1,452.509
95% confidence interval: ±4.306The 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.
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-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.6 Luna: Arena rating from 7,709 published pairwise votes.Muse Wonder: Arena rating from 338 published pairwise votes.
1,461.658
95% confidence interval: ±7.593The 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-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.6 Luna: Arena rating from 11,126 published pairwise votes.Muse Wonder: Arena rating from 487 published pairwise votes.
1,501.073
95% confidence interval: ±6.662The 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-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.6 Luna: Arena rating from 8,615 published pairwise votes.Muse Wonder: Arena rating from 427 published pairwise votes.
1,410.164
95% confidence interval: ±7.596The 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-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena Text, style control Muse Wonder: Snapshot: muse-wonder-max, Reasoning: max, Harness: Arena Text, style controlGPT-5.6 Luna: Arena rating from 16,654 published pairwise votes.Muse Wonder: Arena rating from 802 published pairwise votes.
1,466.961
95% confidence interval: ±5.731The 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.
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-5.6 Luna and Muse Wonder with other leading models using the same data and benchmark logic.
