Compare published benchmark results from matching versions and cohorts, API pricing, and technical specifications. Any documented test setup differences remain visible.
shared result series
214
distinct benchmarks
24
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-Pro
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.
DeepSeek-V4-Pro: peak pricing is $1.32 input / $3.96 output per 1M tokens during Mon, Tue, Wed, Thu, Fri, 01:00-04:00 UTC; Mon, Tue, Wed, Thu, Fri, 06:00-10:00 UTC; off-peak rates apply at all other times.
GPT-5.6 LunaDeepSeek-V4-Pro
API inputUSD per 1M tokens, base tier
GPT-5.6 LunaLower price$0.2
DeepSeek-V4-Pro$0.66
API outputUSD per 1M tokens, base tier
GPT-5.6 LunaLower price$1.2
DeepSeek-V4-Pro$1.98
Cache readUSD per 1M tokens, base tier
GPT-5.6 LunaLower price$0.02
DeepSeek-V4-Pro$0.022
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-Pro
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.
GPT-5.6 Luna
DeepSeek-V4-Pro
Coding: 100 / 76.7 (4 benchmark families)
Reasoning: 100 / 97.5 (1 benchmark family)
Mathematics: 100 / 26.7 (1 benchmark family)
Knowledge: 98.6 / 100 (1 benchmark family)
Finance: 100 / 88.6 (5 benchmark families)
Legal: 77.8 / 86.2 (3 benchmark families)
Agentic tasks: 100 / 74.2 (2 benchmark families)
Productivity: 97.2 / 100 (1 benchmark family)
30 matched rows from 22 benchmark families were considered. The radar shows 8 of 11 comparable categories.
GPT-5.6 LunaDeepSeek-V4-Pro
Code MigrationOverall. Higher is better. No documented setup difference
GPT-5.6 LunaWinner44.55 %
DeepSeek-V4-Pro26.201 %
CorpFin v2Overall. Higher is better. No documented setup difference
GPT-5.6 LunaWinner64.219 %
DeepSeek-V4-Pro61.383 %
CyberBench v1.1Patch. Higher is better. No documented setup difference
GPT-5.6 LunaTie79.661 %
DeepSeek-V4-ProTie79.661 %
EMBOverall. Higher is better. No documented setup difference
GPT-5.6 LunaWinner67.116 %
DeepSeek-V4-Pro51.623 %
Finance Agent (v2)Overall. Higher is better. No documented setup difference
GPT-5.6 LunaWinner55.044 %
DeepSeek-V4-Pro44.083 %
GPQA DiamondOverall. Higher is better. No documented setup difference
GPT-5.6 LunaWinner91.666 %
DeepSeek-V4-Pro89.394 %
Harvey's Legal Agent BenchmarkOverall · Task fully resolved. Higher is better. No documented setup difference
GPT-5.6 Luna1.25 %
DeepSeek-V4-ProWinner3.75 %
IOIIOI 2024. Higher is better. Test setup not documented as identical
GPT-5.6 LunaHigher measured value78 %
DeepSeek-V4-Pro31.333 %
Legal Research BenchOverall · All-pass. Higher is better. No documented setup difference
GPT-5.6 LunaWinner36.538 %
DeepSeek-V4-Pro23.077 %
LegalBenchOverall. Higher is better. No documented setup difference
GPT-5.6 LunaWinner84.034 %
DeepSeek-V4-Pro80.323 %
LMArena Text, Style ControlOverall. Higher is better. Test setup not documented as identical
GPT-5.6 Luna1,453.977
DeepSeek-V4-ProHigher measured value1,457.519
MedCodeOverall. Higher is better. No documented setup difference
GPT-5.6 LunaWinner42.391 %
DeepSeek-V4-Pro40.455 %
Key to the marks:better valuebetter, but not conclusivetie
Benchmark scores for GPT-5.6 Luna and DeepSeek-V4-Pro
Benchmark and task
GPT-5.6 Luna
DeepSeek-V4-Pro
Source
Code MigrationOverallTest 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-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 35,823 anonymous pairwise votes.DeepSeek-V4-Pro: Style-controlled Arena rating from 57,564 anonymous pairwise votes.
1,453.977
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.
Higher measured value1,457.519
95% confidence interval: ±3.905The Arena score measures human preference rather than a fixed capability test. The confidence interval and model configuration are part of the result.
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-Pro: Snapshot: deepseek-v4-pro-high-preview, Reasoning: high, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 35,823 anonymous pairwise votes.DeepSeek-V4-Pro: Style-controlled Arena rating from 54,884 anonymous pairwise votes.
1,453.977
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.
Higher measured value1,454.675
95% confidence interval: ±3.973The 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: 2.1Metric: accuracyScoring: Higher is betterGPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens DeepSeek-V4-Pro: Output limit: 128,000 tokens
No documented difference in the test setupVersion: 1.2Metric: benchmark scoreScoring: Higher is betterSettings: Reasoning: max, Output limit: 128,000 tokens
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-Pro: Snapshot: deepseek-v4-pro, Harness: Arena text, style controlGPT-5.6 Luna: Style-controlled Arena rating from 6,871 anonymous pairwise votes.DeepSeek-V4-Pro: Style-controlled Arena rating from 11,411 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.
1,459.704
95% confidence interval: ±6.73The 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: 2.1Metric: accuracyScoring: Higher is betterGPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens DeepSeek-V4-Pro: Output limit: 128,000 tokens
Test setup not documented as identicalNo direct winnerVersion: 1Metric: mean reviewer code-quality ratingScoring: Higher is betterGPT-5.6 Luna: Reasoning: max, Output limit: 128,000 tokens DeepSeek-V4-Pro: Reasoning: max, Output limit: 384,000 tokens
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-Pro
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-pro-0813
Reasoning setting
high
Pinned endpoint
DeepSeek | deepseek/deepseek-v4-pro-20260813
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-Pro with other leading models using the same data and benchmark logic.
