Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
shared result series
61
distinct benchmarks
3
latest retrieval
2026-09-29
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 GPT-5.6 Luna and DeepSeek-V4-Flash
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 GPT-5.6 Luna and DeepSeek-V4-Flash
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 GPT-5.6 Luna and DeepSeek-V4-Flash
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 1 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 LunaDeepSeek-V4-Flash
CyberBench v1.1Patch. Higher is better. No documented setup difference
GPT-5.6 LunaWinner79.661 %
DeepSeek-V4-Flash72.414 %
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
GPT-5.6 LunaHigher measured value1,453.977
DeepSeek-V4-Flash1,436.082
Taste-BenchOverall. Higher is better. Test setup not documented as identical
GPT-5.6 LunaHigher measured value49 %
DeepSeek-V4-Flash43.3 %
CyberBench v1.1PoC. Higher is better. No documented setup difference
GPT-5.6 LunaWinner88.136 %
DeepSeek-V4-Flash61.017 %
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
GPT-5.6 LunaHigher measured value1,453.977
DeepSeek-V4-Flash1,438.511
LMArena Text, Style ControlBusiness, management and finance. Higher is better. Test setup not documented as identical
GPT-5.6 LunaHigher measured value1,463.458
DeepSeek-V4-Flash1,438.526
LMArena Text, Style ControlBusiness, management and finance. Higher is better. Test setup not documented as identical
GPT-5.6 LunaHigher measured value1,463.458
DeepSeek-V4-Flash1,434.189
LMArena Text, Style ControlChinese. Higher is better. Test setup not documented as identical
GPT-5.6 LunaHigher measured value1,476.096
DeepSeek-V4-Flash1,471.267
LMArena Text, Style ControlChinese. Higher is better. Test setup not documented as identical
GPT-5.6 Luna1,476.096
DeepSeek-V4-FlashHigher measured value1,479.924
LMArena Text, Style ControlCoding. Higher is better. Test setup not documented as identical
GPT-5.6 LunaHigher measured value1,500.651
DeepSeek-V4-Flash1,484.094
LMArena Text, Style ControlCoding. Higher is better. Test setup not documented as identical
GPT-5.6 LunaHigher measured value1,500.651
DeepSeek-V4-Flash1,479.555
LMArena Text, Style ControlCreative writing. Higher is better. Test setup not documented as identical
GPT-5.6 LunaHigher measured value1,411.66
DeepSeek-V4-Flash1,407.791
Key to the marks:better valuebetter, but not conclusivetie
Benchmark scores for GPT-5.6 Luna and DeepSeek-V4-Flash
Benchmark and task
GPT-5.6 Luna
DeepSeek-V4-Flash
Source
CyberBench v1.1PatchTest details
No documented difference in the test setupVersion: 1Metric: accuracyScoring: Higher is better
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 DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 35,823 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 51,871 anonymous pairwise votes.
Higher measured value1,453.977
95% confidence interval: ±4.487The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,436.082
95% confidence interval: ±4.048The 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: arxiv:2609.25804v2Metric: both-orders-correct, engineering/research macro averageScoring: Higher is betterGPT-5.6 Luna: Reasoning: default, Output limit: 65,536 tokens, Attempts: 502 questions, two option orders each DeepSeek-V4-Flash: Reasoning: max, Output limit: 65,536 tokens, Attempts: 502 questions, two option orders eachSame prompt for all models. Each of 502 questions is shown twice with the options reversed. Average of engineering and research success rates, requiring both orders to be correct. 65,536-token output budget; unparseable answers count as wrong.
Higher measured value49 %
0 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
43.3 %
2 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
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 DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 35,823 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 51,747 anonymous pairwise votes.
Higher measured value1,453.977
95% confidence interval: ±4.487The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,438.511
95% confidence interval: ±4.115The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 6,871 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 10,436 anonymous pairwise votes.
Higher measured value1,463.458
95% confidence interval: ±7.984The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,438.526
95% confidence interval: ±6.971The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 6,871 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 10,641 anonymous pairwise votes.
Higher measured value1,463.458
95% confidence interval: ±7.984The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,434.189
95% confidence interval: ±6.982The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 2,848 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 2,996 anonymous pairwise votes.
Higher measured value1,476.096
95% confidence interval: ±11.945The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,471.267
95% confidence interval: ±11.424The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 2,848 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 2,992 anonymous pairwise votes.
1,476.096
95% confidence interval: ±11.945The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Higher measured value1,479.924
95% confidence interval: ±11.42The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 9,953 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 15,262 anonymous pairwise votes.
Higher measured value1,500.651
95% confidence interval: ±6.941The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,484.094
95% confidence interval: ±6.23The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 9,953 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 15,239 anonymous pairwise votes.
Higher measured value1,500.651
95% confidence interval: ±6.941The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,479.555
95% confidence interval: ±6.265The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 7,224 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 8,539 anonymous pairwise votes.
Higher measured value1,411.66
95% confidence interval: ±8.114The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,407.791
95% confidence interval: ±7.543The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 7,224 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 8,638 anonymous pairwise votes.
Higher measured value1,411.66
95% confidence interval: ±8.114The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,410.703
95% confidence interval: ±7.575The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 14,412 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 23,008 anonymous pairwise votes.
Higher measured value1,468.153
95% confidence interval: ±5.981The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,444.92
95% confidence interval: ±5.29The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 14,412 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 22,908 anonymous pairwise votes.
Higher measured value1,468.153
95% confidence interval: ±5.981The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,449.94
95% confidence interval: ±5.323The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 9,172 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 11,179 anonymous pairwise votes.
Higher measured value1,420.336
95% confidence interval: ±7.365The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,404.567
95% confidence interval: ±6.937The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 9,172 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 11,428 anonymous pairwise votes.
Higher measured value1,420.336
95% confidence interval: ±7.365The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,408.063
95% confidence interval: ±6.896The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 26,843 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 39,226 anonymous pairwise votes.
Higher measured value1,456.35
95% confidence interval: ±5.884The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,431.809
95% confidence interval: ±5.308The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 26,843 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 39,391 anonymous pairwise votes.
Higher measured value1,456.35
95% confidence interval: ±5.884The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,436.008
95% confidence interval: ±5.353The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 4,120 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 5,392 anonymous pairwise votes.
Higher measured value1,491.278
95% confidence interval: ±9.879The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,457.264
95% confidence interval: ±8.778The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 4,120 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 5,311 anonymous pairwise votes.
Higher measured value1,491.278
95% confidence interval: ±9.879The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,466.306
95% confidence interval: ±8.867The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 1,142 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 2,006 anonymous pairwise votes.
Higher measured value1,483.582
95% confidence interval: ±18.965The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,448.483
95% confidence interval: ±15.039The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 1,142 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 1,966 anonymous pairwise votes.
Higher measured value1,483.582
95% confidence interval: ±18.965The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,459.263
95% confidence interval: ±15.286The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 613 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 843 anonymous pairwise votes.
Higher measured value1,480.869
95% confidence interval: ±24.898The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,424.769
95% confidence interval: ±21.221The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 613 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 906 anonymous pairwise votes.
Higher measured value1,480.869
95% confidence interval: ±24.898The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,433.595
95% confidence interval: ±20.539The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 23,834 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 34,753 anonymous pairwise votes.
Higher measured value1,475.057
95% confidence interval: ±5.221The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,458.919
95% confidence interval: ±4.767The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 23,834 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 34,700 anonymous pairwise votes.
Higher measured value1,475.057
95% confidence interval: ±5.221The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,458.083
95% confidence interval: ±4.832The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 9,658 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 16,176 anonymous pairwise votes.
Higher measured value1,486.669
95% confidence interval: ±6.97The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,463.433
95% confidence interval: ±6.065The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 9,658 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 16,039 anonymous pairwise votes.
Higher measured value1,486.669
95% confidence interval: ±6.97The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,464.61
95% confidence interval: ±6.133The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 12,879 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 17,961 anonymous pairwise votes.
Higher measured value1,445.83
95% confidence interval: ±6.353The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,428.187
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.
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 DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 12,879 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 18,051 anonymous pairwise votes.
Higher measured value1,445.83
95% confidence interval: ±6.353The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,433.413
95% confidence interval: ±5.881The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 524 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 647 anonymous pairwise votes.
Higher measured value1,433.144
95% confidence interval: ±28.23The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,398.363
95% confidence interval: ±24.906The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 524 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 635 anonymous pairwise votes.
Higher measured value1,433.144
95% confidence interval: ±28.23The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,424.242
95% confidence interval: ±25.166The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 669 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 898 anonymous pairwise votes.
Higher measured value1,412.685
95% confidence interval: ±23.246The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,392.925
95% confidence interval: ±20.977The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 669 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 951 anonymous pairwise votes.
Higher measured value1,412.685
95% confidence interval: ±23.246The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,378.153
95% confidence interval: ±20.872The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 3,026 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 4,139 anonymous pairwise votes.
Higher measured value1,462.12
95% confidence interval: ±11.494The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,447.478
95% confidence interval: ±9.874The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 3,026 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 4,107 anonymous pairwise votes.
Higher measured value1,462.12
95% confidence interval: ±11.494The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,457.491
95% confidence interval: ±9.927The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 5,837 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 8,423 anonymous pairwise votes.
Higher measured value1,459.939
95% confidence interval: ±8.426The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,456.345
95% confidence interval: ±7.388The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 5,837 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 8,509 anonymous pairwise votes.
Higher measured value1,459.939
95% confidence interval: ±8.426The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,459.724
95% confidence interval: ±7.418The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 17,076 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 23,359 anonymous pairwise votes.
Higher measured value1,452.289
95% confidence interval: ±6.017The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,447.83
95% confidence interval: ±5.578The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 17,076 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 23,501 anonymous pairwise votes.
Higher measured value1,452.289
95% confidence interval: ±6.017The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,448.636
95% confidence interval: ±5.577The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 1,659 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 2,688 anonymous pairwise votes.
Higher measured value1,474.058
95% confidence interval: ±14.679The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,425.467
95% confidence interval: ±11.801The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 1,659 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 2,619 anonymous pairwise votes.
Higher measured value1,474.058
95% confidence interval: ±14.679The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,441.412
95% confidence interval: ±11.893The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 1,994 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 2,975 anonymous pairwise votes.
Higher measured value1,483.361
95% confidence interval: ±13.883The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,434.489
95% confidence interval: ±11.462The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 1,994 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 2,828 anonymous pairwise votes.
Higher measured value1,483.361
95% confidence interval: ±13.883The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,445.003
95% confidence interval: ±11.761The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 2,653 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 3,699 anonymous pairwise votes.
1,436.072
95% confidence interval: ±12.409The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Higher measured value1,459.257
95% confidence interval: ±10.503The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 2,653 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 3,774 anonymous pairwise votes.
1,436.072
95% confidence interval: ±12.409The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Higher measured value1,461.307
95% confidence interval: ±10.453The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 5,852 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 9,363 anonymous pairwise votes.
Higher measured value1,456
95% confidence interval: ±8.525The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,453.414
95% confidence interval: ±7.284The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 5,852 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 9,233 anonymous pairwise votes.
Higher measured value1,456
95% confidence interval: ±8.525The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,446.332
95% confidence interval: ±7.34The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 21,398 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 28,862 anonymous pairwise votes.
Higher measured value1,436.495
95% confidence interval: ±5.342The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,423.239
95% confidence interval: ±4.947The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 21,398 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 28,837 anonymous pairwise votes.
Higher measured value1,436.495
95% confidence interval: ±5.342The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,423.125
95% confidence interval: ±5.023The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 532 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 1,030 anonymous pairwise votes.
1,436.589
95% confidence interval: ±25.634The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
Higher measured value1,438.601
95% confidence interval: ±18.712The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 532 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 1,037 anonymous pairwise votes.
Higher measured value1,436.589
95% confidence interval: ±25.634The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,434.977
95% confidence interval: ±18.457The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 4,014 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 5,750 anonymous pairwise votes.
Higher measured value1,448.031
95% confidence interval: ±9.808The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,433.519
95% confidence interval: ±8.502The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 4,014 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 5,790 anonymous pairwise votes.
Higher measured value1,448.031
95% confidence interval: ±9.808The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,437.327
95% confidence interval: ±8.593The 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 ControlSoftware and IT servicesTest 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 DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 14,167 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 21,360 anonymous pairwise votes.
Higher measured value1,492.775
95% confidence interval: ±6.123The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,470.864
95% confidence interval: ±5.508The 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 ControlSoftware and IT servicesTest 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 DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 14,167 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 21,329 anonymous pairwise votes.
Higher measured value1,492.775
95% confidence interval: ±6.123The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,472.722
95% confidence interval: ±5.539The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 1,039 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 1,596 anonymous pairwise votes.
Higher measured value1,461.097
95% confidence interval: ±19.283The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,433.099
95% confidence interval: ±16.059The 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 betterGPT-5.6 Luna: Snapshot: gpt-5.6-luna-xhigh, Reasoning: xhigh, Harness: Arena text, style control DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 1,039 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 1,497 anonymous pairwise votes.
Higher measured value1,461.097
95% confidence interval: ±19.283The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,429.802
95% confidence interval: ±16.45The 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 ControlWriting, literature and languageTest 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 DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 9,607 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 12,557 anonymous pairwise votes.
Higher measured value1,435.176
95% confidence interval: ±7.11The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,415.672
95% confidence interval: ±6.557The 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 ControlWriting, literature and languageTest 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 DeepSeek-V4-Flash: Snapshot: deepseek-v4-flash-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 9,607 anonymous pairwise votes.DeepSeek-V4-Flash: Style-controlled Arena rating from 12,763 anonymous pairwise votes.
Higher measured value1,435.176
95% confidence interval: ±7.11The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
1,422.277
95% confidence interval: ±6.549The 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
Our tests
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.
GPT-5.6 Luna
A community classic for free-form SVG drawing.
Reasoning (requested): high
First attempt
Run date
7 Sept 2026
API provider
openrouter
Requested API model
openai/gpt-5.6-luna
API model reported in response
openai/gpt-5.6-luna
Reasoning setting
high
Pinned endpoint
OpenAI | openai/gpt-5.6-luna-20260709
Temperature
Provider default
Token limit including reasoning
8,192 tokens
Test protocol
community-visual-tests-v1
Technical checks
Passed, not a quality rating
Response time
49.9 s
Visually reviewed. This individual test does not establish overall model quality.
DeepSeek-V4-Flash
API access was unavailable for this run. The model was not evaluated.
Reasoning (requested): high
First attempt
Run date
7 Sept 2026
API provider
openrouter
Requested API model
deepseek/deepseek-v4-flash-0731
Reasoning setting
high
Pinned endpoint
DeepSeek | deepseek/deepseek-v4-flash-20260731
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 GPT-5.6 Luna and DeepSeek-V4-Flash with other leading models using the same data and benchmark logic.
