GPT-5.6 Luna
Unavailable in this round
Language modelActive
GPT-5.6 Luna
OpenAI
- Released
- July 9, 2026
- Data date
- September 8, 2026
- Successor
- GPT-6 Luna
- Benchmark-Meta-Score
- Provisional, 56.1 % panel coverage
- Speed
- 127.8 tokens/sOutput throughput
- Price
- Input · Output / 1M tokens
- Input
- Text, Image
- Output
- Text
GPT-5.6 Luna brought the family’s new tool capabilities to its smallest, lowest-cost tier. Luna could also write programs to coordinate tools and process intermediate results. Paid ChatGPT Work and Codex users could choose its reasoning effort.
GPT-5.6 Sol and GPT-5.6 Terra covered the larger tiers in the same family. OpenAI later named GPT-6 Luna as its successor.
- Position
- Rank 17 of 24
- Index score
- 33.1 / 100
Methodology and source
The LLM comparison hub's selected-panel index averages rank percentiles from 10 documented comparison cohorts. Benchmark meta-scores are shown in the benchmark section.
Benchmark meta-analysis
Overall and area scores
These Gradually indexes place selected published measurements on a 0 to 100 scale. They are not accuracy percentages and do not guarantee results in your application.
Retrieval dates of the sources used 2026-10-15 - 2026-10-19
Overall index
Index 54.9 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Panel-weight coverage
- 56 %
- Test families
- 41 / 71
- Sources
- 3
- Mathematical bounds with missing values
- 30.8-74.7 / 100
Coding
Not enough coverage for a score yet
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Panel-weight coverage
- 49 %
- Test families
- 8 / 15
- Sources
- 2
- Mathematical bounds with missing values
- 26.9-78.0 / 100
Reasoning
Not enough coverage for a score yet
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Panel-weight coverage
- 43 %
- Test families
- 4 / 7
- Sources
- 2
- Mathematical bounds with missing values
- 36.4-93.6 / 100
Mathematics
Not enough coverage for a score yet
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Panel-weight coverage
- 20 %
- Test families
- 1 / 5
- Sources
- 1
- Mathematical bounds with missing values
- 11.8-91.8 / 100
Knowledge
Index 49.9 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Panel-weight coverage
- 67 %
- Test families
- 2 / 3
- Sources
- 2
- Mathematical bounds with missing values
- 33.3-66.6 / 100
Agents
Index 72.9 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Panel-weight coverage
- 50 %
- Test families
- 6 / 12
- Sources
- 2
- Mathematical bounds with missing values
- 36.4-86.4 / 100
General
Index 16.7 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Panel-weight coverage
- 80 %
- Test families
- 4 / 5
- Sources
- 2
- Mathematical bounds with missing values
- 13.4-33.4 / 100
Finance
Index 71.5 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Panel-weight coverage
- 86 %
- Test families
- 6 / 7
- Sources
- 1
- Mathematical bounds with missing values
- 61.3-75.5 / 100
Legal
Index 50.1 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Panel-weight coverage
- 75 %
- Test families
- 3 / 4
- Sources
- 1
- Mathematical bounds with missing values
- 37.6-62.6 / 100
Health
Index 54.0 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Panel-weight coverage
- 67 %
- Test families
- 2 / 3
- Sources
- 1
- Mathematical bounds with missing values
- 36.0-69.3 / 100
Cybersecurity
Not enough coverage for a score yet
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Panel-weight coverage
- 100 %
- Test families
- 1 / 1
- Sources
- 1
- Mathematical bounds with missing values
- 77.3-77.3 / 100
Multimodal
Index 42.4 / 100
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Panel-weight coverage
- 50 %
- Test families
- 2 / 4
- Sources
- 3
- Mathematical bounds with missing values
- 21.2-71.2 / 100
Productivity
Not enough coverage for a score yet
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Panel-weight coverage
- 50 %
- Test families
- 1 / 2
- Sources
- 1
- Mathematical bounds with missing values
- 19.7-69.7 / 100
Education
Not enough coverage for a score yet
provisional
Published configurations differ within this comparison cohort. Treat the index as provisional.
- Panel-weight coverage
- 50 %
- Test families
- 1 / 2
- Sources
- 1
- Mathematical bounds with missing values
- 19.8-69.8 / 100
Documented method · Included test families and measurements
Method version: benchmark-meta-score-v1
The index includes active measurements from reviewed primary sources when at least five models are compared in the same documented comparison slice across dataset, harness, agent, tools, and trial count. Each benchmark series and evaluator contributes one shared setup slice from the newest capture; when dates match, the wider slice is used. When one source and series include several explicitly documented reasoning tiers, the highest documented tier (none through max) is selected, never the best result value. The explicit source label “Non-reasoning” is treated as none. When selecting between multiple results, unknown or ambiguous tiers exclude the model from that series. Unambiguous single configurations do not require a tier ordering. The best individual result for each model is not selected. Equal raw values share the same rank percentile. Multiple series from the same evaluator within a family receive equal weight; evaluators within a family, families within an area, and areas in the overall index then receive equal weight. Unmeasured series remain visible in coverage and bounds. An overall score requires at least four areas, six test families, and two sources. An area score requires at least two test families. Every overall and area score also requires at least 50% of its panel weight.
Published model-specific parameters can differ. This is not a controlled experiment; comparisons with such differences are marked provisional.
Unmeasured portions are not entered as zero. They reduce coverage and contribute only to the displayed bounds. Scores with different coverage are therefore not equally complete.
The bounds hold observed percentiles fixed and allow missing contributions anywhere from 0 to 100. They are not confidence intervals or predictions of future recalculations.
The source count is not a count of independent experiments.
OECD handbook on composite indicatorsAll 41 test families and 12 of 45 raw measurements are listed here. The complete calculation for every model is available in the JSON export.
Test family: AA-Briefcase
Agents · Family index: 74.4 / 100Nominal family weight in the overall panel: 0.6 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-aa-briefcase
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 0.6 %
- Raw value:
- 1,342.18 Elo
- Metric:
- AA-Briefcase Elo
- Version:
- v1.1
- Participating models:
- 83
- Rank percentile within the cohort:
- 74.4 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-aa-briefcase:v1.1:v4.3.2:reasoning:tokens=0:suffix=Max
- Reasoning tier:
- Max
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-aa-briefcase","v1.1","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Setup and model parameters
- Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption.. Reasoning: reasoning enabled. Reasoning effort: Max
Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption.. Source model ID: artificial-analysis/426d24c8-49ae-482a-b4a8-20f1c53f21c1/gpt-5-6-luna/gpt-5-6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Model snapshot: GPT-5.6 Luna (Max). Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Reasoning effort: Max. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: AA-LCR
Reasoning · Family index: 93.9 / 100Nominal family weight in the overall panel: 1.02 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-aa-lcr
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 1.02 %
- Raw value:
- 83.6666666666667 %
- Metric:
- Pass rate
- Version:
- v1.1
- Participating models:
- 83
- Rank percentile within the cohort:
- 93.9 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-aa-lcr:v1.1:v4.3.2:reasoning:tokens=0:suffix=Max
- Reasoning tier:
- Max
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-aa-lcr","v1.1","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Setup and model parameters
- Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption.. Reasoning: reasoning enabled. Reasoning effort: Max
Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption.. Source model ID: artificial-analysis/426d24c8-49ae-482a-b4a8-20f1c53f21c1/gpt-5-6-luna/gpt-5-6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Model snapshot: GPT-5.6 Luna (Max). Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Reasoning effort: Max. Score display: 83.7%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: APEX-Agents-AA
Agents · Family index: 80.8 / 100Nominal family weight in the overall panel: 0.6 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-apex-agents-aa
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 0.6 %
- Raw value:
- 35.8407079646018 %
- Metric:
- Pass@1 success rate
- Version:
- AA public cohort: 452 tasks
- Participating models:
- 27
- Rank percentile within the cohort:
- 80.8 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-apex-agents-aa:AA public cohort: 452 tasks:standalone:reasoning:tokens=0:suffix=Max
- Reasoning tier:
- Max
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-apex-agents-aa","AA public cohort: 452 tasks","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Harness:
- Artificial Analysis Stirrup
- Agent:
- Stirrup agent
- Tool policy:
- 200-turn cap; MCP-backed workplace tools in Archipelago
- Attempts:
- pass@1, averaged over 3 repeats per task
- Setup and model parameters
- Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption. 452 tasks from the public 480-task release, with three repeats per task. A run passes only if every rubric criterion is satisfied; the leaderboard averages pass@1 across repeats.. Harness: Artificial Analysis Stirrup. Agent: Stirrup agent. Tool policy: 200-turn cap; MCP-backed workplace tools in Archipelago. Attempts: pass@1, averaged over 3 repeats per task. Reasoning: reasoning enabled. Reasoning effort: Max
Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption. 452 tasks from the public 480-task release, with three repeats per task. A run passes only if every rubric criterion is satisfied; the leaderboard averages pass@1 across repeats.. Source model ID: artificial-analysis/426d24c8-49ae-482a-b4a8-20f1c53f21c1/gpt-5-6-luna/gpt-5-6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Model snapshot: GPT-5.6 Luna (Max). Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Harness: Artificial Analysis Stirrup. Agent: Stirrup agent. Tool policy: 200-turn cap; MCP-backed workplace tools in Archipelago. Attempts: pass@1, averaged over 3 repeats per task. Reasoning: reasoning enabled. Reasoning effort: Max. Score display: 35.8%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: AutomationBench-AA
Agents · Family index: 68.3 / 100Nominal family weight in the overall panel: 0.6 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-automationbench-aa
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 0.6 %
- Raw value:
- 50.208617637561936 %
- Metric:
- Objectives completed without guardrail violations
- Version:
- unspecified
- Participating models:
- 83
- Rank percentile within the cohort:
- 68.3 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-automationbench-aa:unspecified:v4.3.2:reasoning:tokens=0:suffix=Max
- Reasoning tier:
- Max
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-automationbench-aa","unspecified","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Setup and model parameters
- Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption.. Reasoning: reasoning enabled. Reasoning effort: Max
Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption.. Source model ID: artificial-analysis/426d24c8-49ae-482a-b4a8-20f1c53f21c1/gpt-5-6-luna/gpt-5-6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Model snapshot: GPT-5.6 Luna (Max). Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Reasoning effort: Max. Score display: 50.2%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: GDP.pdf
Reasoning · Family index: 90.2 / 100Nominal family weight in the overall panel: 1.02 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-gdp-pdf
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 1.02 %
- Raw value:
- 24 %
- Metric:
- All-pass rate
- Version:
- unspecified
- Participating models:
- 83
- Rank percentile within the cohort:
- 90.2 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-gdp-pdf:unspecified:v4.3.2:reasoning:tokens=0:suffix=Max
- Reasoning tier:
- Max
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-gdp-pdf","unspecified","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Setup and model parameters
- Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption.. Reasoning: reasoning enabled. Reasoning effort: Max
Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption.. Source model ID: artificial-analysis/426d24c8-49ae-482a-b4a8-20f1c53f21c1/gpt-5-6-luna/gpt-5-6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Model snapshot: GPT-5.6 Luna (Max). Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Reasoning effort: Max. Score display: 24.0%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: GDPval-AA
Agents · Family index: 76.8 / 100Nominal family weight in the overall panel: 0.6 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-gdpval-aa
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 0.6 %
- Raw value:
- 1,459.2 Elo
- Metric:
- GDPval-AA Elo
- Version:
- v2.1
- Participating models:
- 83
- Rank percentile within the cohort:
- 76.8 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-gdpval-aa:v2.1:v4.3.2:reasoning:tokens=0:suffix=Max
- Reasoning tier:
- Max
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-gdpval-aa","v2.1","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Setup and model parameters
- Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption.. Reasoning: reasoning enabled. Reasoning effort: Max
Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption.. Source model ID: artificial-analysis/426d24c8-49ae-482a-b4a8-20f1c53f21c1/gpt-5-6-luna/gpt-5-6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Model snapshot: GPT-5.6 Luna (Max). Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Reasoning effort: Max. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: ITBench-AA (SRE)
Agents · Family index: 54.3 / 100Nominal family weight in the overall panel: 0.6 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-itbench-aa
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 0.6 %
- Raw value:
- 40.3201506591337 %
- Metric:
- Average precision at full recall
- Version:
- AA cohort: 59 tasks
- Participating models:
- 36
- Rank percentile within the cohort:
- 54.3 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-itbench-aa:AA cohort: 59 tasks:standalone:reasoning:tokens=0:suffix=Max
- Reasoning tier:
- Max
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-itbench-aa","AA cohort: 59 tasks","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Harness:
- Artificial Analysis Stirrup
- Agent:
- Stirrup agent
- Tool policy:
- Shell access to an offline Kubernetes incident snapshot
- Attempts:
- Average precision at full recall, 3 repeats per task
- Setup and model parameters
- Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption. 59 Kubernetes incident tasks, 40 public and 19 private, with three repeats per task. A run scores zero if it misses any true root cause; otherwise it receives its precision at full recall. This is the SRE slice of ITBench.. Harness: Artificial Analysis Stirrup. Agent: Stirrup agent. Tool policy: Shell access to an offline Kubernetes incident snapshot. Attempts: Average precision at full recall, 3 repeats per task. Reasoning: reasoning enabled. Reasoning effort: Max
Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption. 59 Kubernetes incident tasks, 40 public and 19 private, with three repeats per task. A run scores zero if it misses any true root cause; otherwise it receives its precision at full recall. This is the SRE slice of ITBench.. Source model ID: artificial-analysis/426d24c8-49ae-482a-b4a8-20f1c53f21c1/gpt-5-6-luna/gpt-5-6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Model snapshot: GPT-5.6 Luna (Max). Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Harness: Artificial Analysis Stirrup. Agent: Stirrup agent. Tool policy: Shell access to an offline Kubernetes incident snapshot. Attempts: Average precision at full recall, 3 repeats per task. Reasoning: reasoning enabled. Reasoning effort: Max. Score display: 40.3%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: AA-Omniscience
Knowledge · Family index: 42.7 / 100Nominal family weight in the overall panel: 2.38 % · Coverage of this test family: 100 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-omniscience
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 2.38 %
- Raw value:
- -10.283333333333333 points
- Metric:
- AA-Omniscience Index
- Version:
- unspecified
- Participating models:
- 83
- Rank percentile within the cohort:
- 42.7 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-omniscience:unspecified:v4.3.2:reasoning:tokens=0:suffix=Max
- Reasoning tier:
- Max
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-omniscience","unspecified","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Setup and model parameters
- Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption.. Reasoning: reasoning enabled. Reasoning effort: Max
Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption.. Source model ID: artificial-analysis/426d24c8-49ae-482a-b4a8-20f1c53f21c1/gpt-5-6-luna/gpt-5-6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Model snapshot: GPT-5.6 Luna (Max). Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Reasoning effort: Max. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: GPQA Diamond
Reasoning · Family index: 78.3 / 100Nominal family weight in the overall panel: 1.02 % · Coverage of this test family: 50 %
- Vals AI
Published configurations differ within this cohort.
- Measurement:
- vals-gpqa
- Series weight within the test family:
- 50 %
- Nominal contribution to the overall panel:
- 0.51 %
- Raw value:
- 91.666 %
- Metric:
- accuracy
- Version:
- 1
- Participating models:
- 77
- Rank percentile within the cohort:
- 78.3 %
- Retrieved:
- 2026-10-15
- Comparison cohort:
- vals-gpqa:1:overall
- Reasoning tier:
- max
- Documented comparison setup
- Publication cohort:
- vals-gpqa:1:overall
- Dataset type:
- public
- Setup and model parameters
- Reasoning effort: max. Maximum output tokens: 128000
Source model ID: openai/gpt-5.6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-09-01. Reasoning effort: max. Maximum output tokens: 128000. Latency in seconds: 53.521. Standard error: 1.736. Cost per task in USD: 0.010616. Source ID: vals-ai. Evidence capture ID: vals-gpqa-2026-10-15-951eb5224097. Source payload hash: 951eb5224097733a9d09d06c14908ae2980e2e640e539f2c284877c5092d7077. Parser version: vals-astro-v3. Imported at: 2026-10-15
- Vals AI
Test family: Humanity’s Last Exam
Reasoning · Family index: 63.4 / 100Nominal family weight in the overall panel: 1.02 % · Coverage of this test family: 50 %
- Artificial Analysis
Published configurations differ within this cohort.
- Measurement:
- artificial-analysis-humanitys-last-exam
- Series weight within the test family:
- 50 %
- Nominal contribution to the overall panel:
- 0.51 %
- Raw value:
- 39.4810009267841 %
- Metric:
- Text-only pass@1 accuracy
- Version:
- unspecified
- Participating models:
- 83
- Rank percentile within the cohort:
- 63.4 %
- Retrieved:
- 2026-10-19
- Comparison cohort:
- artificial-analysis-humanitys-last-exam:unspecified:v4.3.2:reasoning:tokens=0:suffix=Max
- Reasoning tier:
- Max
- Documented comparison setup
- Publication cohort:
- ["artificial-analysis-humanitys-last-exam","unspecified","aa-model-page-2026-10-19-8a022369738c"]
- Dataset type:
- artificial-analysis-evaluation
- Setup and model parameters
- Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption.. Reasoning: reasoning enabled. Reasoning effort: Max
Exact AA configuration: GPT-5.6 Luna (Max) (release gpt-5-6-luna, row gpt-5-6-luna, UUID 426d24c8-49ae-482a-b4a8-20f1c53f21c1, reasoning=true, source reasoning-token configuration budget=0, suffix=Max). This configured value is not measured token consumption.. Source model ID: artificial-analysis/426d24c8-49ae-482a-b4a8-20f1c53f21c1/gpt-5-6-luna/gpt-5-6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Model snapshot: GPT-5.6 Luna (Max). Evaluator: Artificial Analysis. Dataset type: artificial-analysis-evaluation. Reasoning: reasoning enabled. Reasoning effort: Max. Score display: 39.5%. Source ID: artificial-analysis. Evidence capture ID: aa-model-page-2026-10-19-8a022369738c. Source payload hash: 8a022369738cbe2a0e2f9bf486a2882865dbb0c6f1396dfec84059a802560e3c. Parser version: artificial-analysis-rsc-models-v2. Imported at: 2026-10-19
- Artificial Analysis
Test family: LMArena Text, Style Control
General · Family index: 19.4 / 100Nominal family weight in the overall panel: 1.43 % · Coverage of this test family: 100 %
- LMArena
Published configurations differ within this cohort.
- Measurement:
- lmarena-text-style-control
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 1.43 %
- Raw value:
- 1,452.509427905681 rating
- Metric:
- style-controlled Bradley-Terry rating
- Version:
- style-control-v1
- Participating models:
- 37
- Rank percentile within the cohort:
- 19.4 %
- Retrieved:
- 2026-10-15
- Comparison cohort:
- lmarena-text-style-control:2026-10-13:overall
- Reasoning tier:
- xhigh
- Documented comparison setup
- Publication cohort:
- lmarena-text-style-control:2026-10-13:overall
- Dataset type:
- public-crowdsourced-preferences
- Harness:
- Arena Text, style control
- Setup and model parameters
- Arena rating from 41,103 published pairwise votes.. Harness: Arena Text, style control. Reasoning effort: xhigh
Arena rating from 41,103 published pairwise votes.. Source model ID: lmarena/gpt-5.6-luna-xhigh. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Model snapshot: gpt-5.6-luna-xhigh. Evaluator: LMArena. Dataset type: public-crowdsourced-preferences. Leaderboard date: 2026-10-13. Harness: Arena Text, style control. Reasoning effort: xhigh. Source ID: lmarena. Evidence capture ID: lmarena-4589dee83b594891961ae5190c508a9288d2c2ae-a39cbed99996. Source payload hash: a39cbed99996f4993a4cd66d8322b2edb939f1ffdbd377c9d3769edd01dd78ca. Parser version: lmarena-dataset-v1. Imported at: 2026-10-15
- LMArena
Test family: LMArena Vision, Style Control
Multimodal · Family index: 23.3 / 100Nominal family weight in the overall panel: 1.79 % · Coverage of this test family: 100 %
- LMArena
Published configurations differ within this cohort.
- Measurement:
- lmarena-vision-style-control
- Series weight within the test family:
- 100 %
- Nominal contribution to the overall panel:
- 1.79 %
- Raw value:
- 1,257.6616631426245 rating
- Metric:
- style-controlled Bradley-Terry rating
- Version:
- style-control-v1
- Participating models:
- 31
- Rank percentile within the cohort:
- 23.3 %
- Retrieved:
- 2026-10-15
- Comparison cohort:
- lmarena-vision-style-control:2026-10-09:overall
- Reasoning tier:
- xhigh
- Documented comparison setup
- Publication cohort:
- lmarena-vision-style-control:2026-10-09:overall
- Dataset type:
- public-crowdsourced-preferences
- Harness:
- Arena Vision, style control
- Setup and model parameters
- Arena rating from 11,086 published pairwise votes.. Harness: Arena Vision, style control. Reasoning effort: xhigh
Arena rating from 11,086 published pairwise votes.. Source model ID: lmarena/gpt-5.6-luna-xhigh. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Model snapshot: gpt-5.6-luna-xhigh. Evaluator: LMArena. Dataset type: public-crowdsourced-preferences. Leaderboard date: 2026-10-09. Harness: Arena Vision, style control. Reasoning effort: xhigh. Source ID: lmarena. Evidence capture ID: lmarena-vision_style_control-4589dee83b594891961ae5190c508a9288d2c2ae-6cf1fae8efc9. Source payload hash: 6cf1fae8efc9ef6fe066f27d5bbe558cd360803a9c0fa6d89905aa53934efdb4. Parser version: lmarena-dataset-v1. Imported at: 2026-10-15
- LMArena
Test family: MMMU-Pro
Multimodal · Family index: 61.5 / 100Nominal family weight in the overall panel: 1.79 % · Coverage of this test family: 100 %
Test family: SWE-bench Verified
Coding · Family index: 88.1 / 100Nominal family weight in the overall panel: 0.48 % · Coverage of this test family: 50 %
Test family: Terminal-Bench
Coding · Family index: 63.2 / 100Nominal family weight in the overall panel: 0.48 % · Coverage of this test family: 83 %
Test family: Terminal-Bench Science
Coding · Family index: 13.3 / 100Nominal family weight in the overall panel: 0.48 % · Coverage of this test family: 100 %
Test family: BioMysteryBench
General · Family index: 13.2 / 100Nominal family weight in the overall panel: 1.43 % · Coverage of this test family: 100 %
Test family: Code Migration
Coding · Family index: 71.0 / 100Nominal family weight in the overall panel: 0.48 % · Coverage of this test family: 100 %
Test family: CorpFin v2
Finance · Family index: 64.9 / 100Nominal family weight in the overall panel: 1.02 % · Coverage of this test family: 100 %
Test family: CyberBench v1.1
Cybersecurity · Family index: 77.3 / 100Nominal family weight in the overall panel: 7.14 % · Coverage of this test family: 100 %
Test family: EMB
Finance · Family index: 76.3 / 100Nominal family weight in the overall panel: 1.02 % · Coverage of this test family: 100 %
Test family: Finance Agent (v2)
Finance · Family index: 76.7 / 100Nominal family weight in the overall panel: 1.02 % · Coverage of this test family: 100 %
Test family: IOI
Coding · Family index: 57.6 / 100Nominal family weight in the overall panel: 0.48 % · Coverage of this test family: 100 %
Test family: Harvey's Legal Agent Benchmark
Legal · Family index: 31.1 / 100Nominal family weight in the overall panel: 1.79 % · Coverage of this test family: 100 %
Test family: LegalBench
Legal · Family index: 64.1 / 100Nominal family weight in the overall panel: 1.79 % · Coverage of this test family: 100 %
Test family: Legal Research Bench
Legal · Family index: 55.0 / 100Nominal family weight in the overall panel: 1.79 % · Coverage of this test family: 100 %
Test family: MedCode
Health · Family index: 44.8 / 100Nominal family weight in the overall panel: 2.38 % · Coverage of this test family: 100 %
Test family: MedScribe
Health · Family index: 63.2 / 100Nominal family weight in the overall panel: 2.38 % · Coverage of this test family: 100 %
Test family: MMLU-Pro
Knowledge · Family index: 57.1 / 100Nominal family weight in the overall panel: 2.38 % · Coverage of this test family: 100 %
Test family: MortgageTax
Finance · Family index: 61.5 / 100Nominal family weight in the overall panel: 1.02 % · Coverage of this test family: 100 %
Test family: MysteryMechanism
General · Family index: 5.0 / 100Nominal family weight in the overall panel: 1.43 % · Coverage of this test family: 100 %
Test family: ProgramBench
Coding · Family index: 24.5 / 100Nominal family weight in the overall panel: 0.48 % · Coverage of this test family: 100 %
Test family: ProofBench
Mathematics · Family index: 59.0 / 100Nominal family weight in the overall panel: 1.43 % · Coverage of this test family: 100 %
Test family: SAGE
Education · Family index: 39.7 / 100Nominal family weight in the overall panel: 3.57 % · Coverage of this test family: 100 %
Test family: SkillsBench
Agents · Family index: 82.8 / 100Nominal family weight in the overall panel: 0.6 % · Coverage of this test family: 100 %
Test family: Public Benefits Bench v1.1
Productivity · Family index: 39.5 / 100Nominal family weight in the overall panel: 3.57 % · Coverage of this test family: 100 %
Test family: SRE Bench
General · Family index: 29.2 / 100Nominal family weight in the overall panel: 1.43 % · Coverage of this test family: 100 %
Test family: Tax Agent Bench
Finance · Family index: 52.7 / 100Nominal family weight in the overall panel: 1.02 % · Coverage of this test family: 100 %
Test family: TaxEval v2
Finance · Family index: 96.7 / 100Nominal family weight in the overall panel: 1.02 % · Coverage of this test family: 100 %
Test family: Vibe Code Bench 1-100
Coding · Family index: 71.4 / 100Nominal family weight in the overall panel: 0.48 % · Coverage of this test family: 100 %
Test family: Vibe Code Bench v1.1
Coding · Family index: 69.4 / 100Nominal family weight in the overall panel: 0.48 % · Coverage of this test family: 100 %
Benchmark sources at a glance
Each evaluator measures different capabilities under its own conditions. Test series, composite indices and their components stay separate. The detailed results below retain their scales, configurations and source dates.
| Evaluator | Test series | Composite indices | Recorded active measurements |
|---|---|---|---|
| Artificial Analysis | 12 | 1 | 75 |
| Vals AI | 31 | 2 | 217 |
| LMArena | 2 | 0 | 37 |
| ARC Prize | 2 | 0 | 6 |
Coverage is not a quality ranking. Overlapping tests and multiple settings do not count as independent experiments. Vendor claims, historical and disputed results are excluded from this overview and remain labelled in the detailed evidence.
Page 1 of 33
Published benchmarks
BrowseComp
Overall
1,266 hard-to-find research tasks with short, unambiguous answers. The benchmark rewards persistent fact finding and only partly represents open-ended research reports or typical user questions.
Note (GPT-5.6 Luna): Editorial selection from the vendor table, not a complete extract of the comparison cohort.
1.Claude Mythos 588%
Note: Editorial selection from the vendor table, not a complete extract of the comparison cohort.
2.GPT-5.6 Terra87.5%
Note: Editorial selection from the vendor table, not a complete extract of the comparison cohort.
3.Gemini 3.1 Pro Preview85.9%
Note: Editorial selection from the vendor table, not a complete extract of the comparison cohort.
4.GPT-5.584.4%
Note: Editorial selection from the vendor table, not a complete extract of the comparison cohort.
5.Claude Opus 4.884.3%
Note: Editorial selection from the vendor table, not a complete extract of the comparison cohort.
higher is betterAs of September 2, 2026Scale: 0% - 100%
Methodology and context
- Comparison cohort
- browsecomp-openai-gpt-5-6-table
- Metric
- accuracy
- Scale
- 0-100
- Participants
- 6
- Methodology and context
- Cross-vendor comparison table with browsing tools. Exact agent systems differ.. Source model ID: curated/gpt-5.6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Evaluator: OpenAI. Dataset type: public. Leaderboard date: 2026-07-09. Source ID: openai. Evidence capture ID: curated-openai-2026-09-02-0bd098ab97ca. Source payload hash: 0bd098ab97cafde3feadf3a100bb234ae5adef4eaf9ce6c434ec1e5b482dc234. Parser version: curated-v1. Imported at: 2026-10-15
Taste-Bench
Overall
502 technical decision points from engineering and research workflows. Each choice is presented in both answer orders. The overall score averages engineering and research and requires both answer orders to be correct. Unparseable responses count as wrong. Reasoning settings and output budget are part of the setup.
Note (GPT-5.6 Luna): 0 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
1.GPT-5.6 Sol59.7%
Note: 0 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
2.GPT-5.559.5%
Note: 0 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
3.Claude Opus 555.5%
Note: 0 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
4.Grok 4.554.6%
Note: 10 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
5.GPT-5.6 Terra54%
Note: 0 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
6.GLM-5.253.9%
Note: 17 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
7.Claude Sonnet 551.6%
Note: 0 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
9.MiniMax M345.3%
Note: 3 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
10.DeepSeek-V4-Flash43.3%
Note: 2 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
11.GPT-5.4 mini40.1%
Note: 112 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
12.Mistral Medium 3.537.7%
Note: 24 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
13.GPT-5.4 nano36.6%
Note: 93 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
14.Grok 4.20 Reasoning15.7%
Note: 459 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
higher is betterAs of September 26, 2026Scale: 0% - 100%
Methodology and context
- Comparison cohort
- taste-bench-paper-v2-502
- Metric
- both-orders-correct, engineering/research macro average
- Scale
- 0-100
- Participants
- 14
- Methodology and context
- Same 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.. Source model ID: curated/gpt-5.6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Evaluator: Taste-Bench paper. Dataset type: public. Leaderboard date: 2026-09-23. Attempts: 502 questions, two option orders each. Reasoning effort: default. Maximum output tokens: 65536. Source ID: taste-bench-paper. Evidence capture ID: curated-taste-bench-paper-2026-09-26-e987b25f0249. Source payload hash: e987b25f02493f106fbc05ee9ce4784e0b4d3daaef03842f3698958a7aa01f63. Parser version: curated-v1. Imported at: 2026-10-15
General tasks
BioMysteryBench
| Sub-task | GPT-5.6 Luna (This model) | GPT-6.1 Sol | GPT-6 Astra | GPT-6 Sol | GPT-5.6 Sol | GPT-6 Luna |
|---|---|---|---|---|---|---|
| Hard | 27.45% | 39.22% (best value in this row) | 37.26% | 35.29% | 29.41% | 17.65% |
| Human-solvable | 69.41% | 89.04% (best value in this row) | 89.04% (best value in this row) | 84.02% | 80.82% | 71.69% |
| Overall | 61.48% | 79.63% (best value in this row) | 79.26% | 74.82% | 71.11% | 61.48% |
higher is betterAs of October 15, 2026Source: Vals AIbars scaled within each row, not across rows
Methodology and context
- Metric
- accuracy
Coding
Code Migration
| Sub-task | GPT-5.6 Luna (This model) | GPT-6 Astra | GPT-6.1 Sol | GPT-6 Sol | GPT-5.6 Sol | GPT-5.6 Terra | GPT-6 Luna |
|---|---|---|---|---|---|---|---|
| CLI | 36.07% | 67.46% (best value in this row) | 63.5% | 52.93% | 47.22% | 40.41% | 37.22% |
| COBOL | 70% (best value in this row) | 68.57% | 70% (best value in this row) | 70% (best value in this row) | 70% (best value in this row) | 70% (best value in this row) | 58.57% |
| Overall | 44.55% | 67.74% (best value in this row) | 65.12% | 57.2% | 52.92% | 47.8% | 42.55% |
higher is betterAs of October 15, 2026Source: Vals AIbars scaled within each row, not across rows
Methodology and context
- Metric
- accuracy
Code Migration
Code Quality
higher is betterAs of October 15, 2026Scale: 0 rating - 4.5 rating
Methodology and context
- Comparison cohort
- vals-code-migration:1:code_quality
- Metric
- mean reviewer code-quality rating
- Scale
- No upper bound is documented. The chart spans the recorded values and zero.
- Participants
- 7
- Methodology and context
- Source model ID: openai/gpt-5.6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-12. Reasoning effort: max. Maximum output tokens: 128000. Latency in seconds: 3514.758. Standard error: 0.065. Cost per task in USD: 1.882918. Score display: 3.195 / 5. Source ID: vals-ai. Evidence capture ID: vals-code-migration-2026-10-15-3fa9c10568ec. Source payload hash: 3fa9c10568ecc117fabec81767c405b49a25d5d2ded308ee435fffb197c53474. Parser version: vals-astro-v3. Imported at: 2026-10-15
Recorded measurement details
BrowseComp: Overall (Show measurement, test conditions, and source)
- Source value
- 83.3
- Score
- 83.3
- Metric
- accuracy
- Unit
- %
- Benchmark version
- 1,266 tasks
- Category
- search
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- browsecomp-openai-gpt-5-6-table
- Source type
- vendor-reported
- Evaluator
- OpenAI
- Status
- active
- Retrieved at
- 2026-09-02
- Methodology
- Cross-vendor comparison table with browsing tools. Exact agent systems differ.. Source model ID: curated/gpt-5.6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Evaluator: OpenAI. Dataset type: public. Leaderboard date: 2026-07-09. Source ID: openai. Evidence capture ID: curated-openai-2026-09-02-0bd098ab97ca. Source payload hash: 0bd098ab97cafde3feadf3a100bb234ae5adef4eaf9ce6c434ec1e5b482dc234. Parser version: curated-v1. Imported at: 2026-10-15
- Comparison methodology
- Cross-vendor comparison table with browsing tools. Exact agent systems differ.
- Context
- Editorial selection from the vendor table, not a complete extract of the comparison cohort.
Taste-Bench: Overall (Show measurement, test conditions, and source)
- Source value
- 49
- Score
- 49
- Metric
- both-orders-correct, engineering/research macro average
- Unit
- %
- Benchmark version
- arxiv:2609.25804v2
- Category
- agentic
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- taste-bench-paper-v2-502
- Source type
- independent-evaluator
- Evaluator
- Taste-Bench paper
- Status
- active
- Retrieved at
- 2026-09-26
- Methodology
- Same 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.. Source model ID: curated/gpt-5.6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Evaluator: Taste-Bench paper. Dataset type: public. Leaderboard date: 2026-09-23. Attempts: 502 questions, two option orders each. Reasoning effort: default. Maximum output tokens: 65536. Source ID: taste-bench-paper. Evidence capture ID: curated-taste-bench-paper-2026-09-26-e987b25f0249. Source payload hash: e987b25f02493f106fbc05ee9ce4784e0b4d3daaef03842f3698958a7aa01f63. Parser version: curated-v1. Imported at: 2026-10-15
- Comparison methodology
- Same 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.
- Context
- 0 of 1,004 responses were unparseable and counted as wrong. Not a Gradually test.
BioMysteryBench: Hard (Show measurement, test conditions, and source)
- Source value
- 27.451
- Score
- 27.451
- Metric
- accuracy
- Unit
- %
- Benchmark version
- 1
- Category
- general
- Task
- human_difficult
- Task label
- Hard
- Direction
- Higher is better
- Comparison cohort
- vals-biomysterybench:1:human_difficult
- Source type
- independent-evaluator
- Evaluator
- Vals AI
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Source model ID: openai/gpt-5.6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-10-12. Harness: Terminus 2. Reasoning effort: max. Maximum output tokens: 128000. Latency in seconds: 1111.274. Standard error: 5.188. Cost per task in USD: 0.13563. Source ID: vals-ai. Evidence capture ID: vals-biomysterybench-2026-10-15-59bf79d38ec4. Source payload hash: 59bf79d38ec415a34ffb1c2901a16ecbbe101b7fa864e86104d2571fc7cfc23d. Parser version: vals-astro-v3. Imported at: 2026-10-15
- Comparison methodology
- Harness: Terminus 2. Reasoning effort: max. Maximum output tokens: 128000
BioMysteryBench: Human-solvable (Show measurement, test conditions, and source)
- Source value
- 69.406
- Score
- 69.406
- Metric
- accuracy
- Unit
- %
- Benchmark version
- 1
- Category
- general
- Task
- human_solvable
- Task label
- Human-solvable
- Direction
- Higher is better
- Comparison cohort
- vals-biomysterybench:1:human_solvable
- Source type
- independent-evaluator
- Evaluator
- Vals AI
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Source model ID: openai/gpt-5.6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-10-12. Harness: Terminus 2. Reasoning effort: max. Maximum output tokens: 128000. Latency in seconds: 1111.274. Standard error: 1.99. Cost per task in USD: 0.077816. Source ID: vals-ai. Evidence capture ID: vals-biomysterybench-2026-10-15-59bf79d38ec4. Source payload hash: 59bf79d38ec415a34ffb1c2901a16ecbbe101b7fa864e86104d2571fc7cfc23d. Parser version: vals-astro-v3. Imported at: 2026-10-15
- Comparison methodology
- Harness: Terminus 2. Reasoning effort: max. Maximum output tokens: 128000
BioMysteryBench: Overall (Show measurement, test conditions, and source)
- Source value
- 61.481
- Score
- 61.481
- Metric
- accuracy
- Unit
- %
- Benchmark version
- 1
- Category
- general
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- vals-biomysterybench:1:overall
- Source type
- independent-evaluator
- Evaluator
- Vals AI
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Source model ID: openai/gpt-5.6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Evaluator: Vals AI. Dataset type: public. Leaderboard date: 2026-10-12. Harness: Terminus 2. Reasoning effort: max. Maximum output tokens: 128000. Latency in seconds: 1111.274. Standard error: 0.741. Cost per task in USD: 0.088859. Source ID: vals-ai. Evidence capture ID: vals-biomysterybench-2026-10-15-59bf79d38ec4. Source payload hash: 59bf79d38ec415a34ffb1c2901a16ecbbe101b7fa864e86104d2571fc7cfc23d. Parser version: vals-astro-v3. Imported at: 2026-10-15
- Comparison methodology
- Harness: Terminus 2. Reasoning effort: max. Maximum output tokens: 128000
Code Migration: CLI (Show measurement, test conditions, and source)
- Source value
- 36.067
- Score
- 36.067
- Metric
- accuracy
- Unit
- %
- Benchmark version
- 1
- Category
- coding
- Task
- cli
- Task label
- CLI
- Direction
- Higher is better
- Comparison cohort
- vals-code-migration:1:cli
- Source type
- independent-evaluator
- Evaluator
- Vals AI
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Source model ID: openai/gpt-5.6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-12. Reasoning effort: max. Maximum output tokens: 128000. Latency in seconds: 4387.047. Standard error: 2.468. Cost per task in USD: 2.425297. Source ID: vals-ai. Evidence capture ID: vals-code-migration-2026-10-15-3fa9c10568ec. Source payload hash: 3fa9c10568ecc117fabec81767c405b49a25d5d2ded308ee435fffb197c53474. Parser version: vals-astro-v3. Imported at: 2026-10-15
- Comparison methodology
- Reasoning effort: max. Maximum output tokens: 128000
Code Migration: COBOL (Show measurement, test conditions, and source)
- Source value
- 70
- Score
- 70
- Metric
- accuracy
- Unit
- %
- Benchmark version
- 1
- Category
- coding
- Task
- cobol
- Task label
- COBOL
- Direction
- Higher is better
- Comparison cohort
- vals-code-migration:1:cobol
- Source type
- independent-evaluator
- Evaluator
- Vals AI
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Source model ID: openai/gpt-5.6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-12. Reasoning effort: max. Maximum output tokens: 128000. Latency in seconds: 897.888. Standard error: 15.275. Cost per task in USD: 0.255782. Source ID: vals-ai. Evidence capture ID: vals-code-migration-2026-10-15-3fa9c10568ec. Source payload hash: 3fa9c10568ecc117fabec81767c405b49a25d5d2ded308ee435fffb197c53474. Parser version: vals-astro-v3. Imported at: 2026-10-15
- Comparison methodology
- Reasoning effort: max. Maximum output tokens: 128000
Code Migration: Overall (Show measurement, test conditions, and source)
- Source value
- 44.55
- Score
- 44.55
- Metric
- accuracy
- Unit
- %
- Benchmark version
- 1
- Category
- coding
- Task
- overall
- Task label
- Overall
- Direction
- Higher is better
- Comparison cohort
- vals-code-migration:1:overall
- Source type
- independent-evaluator
- Evaluator
- Vals AI
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Source model ID: openai/gpt-5.6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-12. Reasoning effort: max. Maximum output tokens: 128000. Latency in seconds: 3514.758. Standard error: 4.244. Cost per task in USD: 1.882918. Source ID: vals-ai. Evidence capture ID: vals-code-migration-2026-10-15-3fa9c10568ec. Source payload hash: 3fa9c10568ecc117fabec81767c405b49a25d5d2ded308ee435fffb197c53474. Parser version: vals-astro-v3. Imported at: 2026-10-15
- Comparison methodology
- Reasoning effort: max. Maximum output tokens: 128000
Code Migration: Code Quality (Show measurement, test conditions, and source)
- Source value
- 3.195
- Score
- 3.195
- Metric
- mean reviewer code-quality rating
- Unit
- rating
- Benchmark version
- 1
- Category
- coding
- Task
- code_quality
- Task label
- Code Quality
- Direction
- Higher is better
- Comparison cohort
- vals-code-migration:1:code_quality
- Source type
- independent-evaluator
- Evaluator
- Vals AI
- Status
- active
- Retrieved at
- 2026-10-15
- Methodology
- Source model ID: openai/gpt-5.6-luna. Source model name: GPT-5.6 Luna. Provider reported by source: OpenAI. Evaluator: Vals AI. Dataset type: private. Leaderboard date: 2026-10-12. Reasoning effort: max. Maximum output tokens: 128000. Latency in seconds: 3514.758. Standard error: 0.065. Cost per task in USD: 1.882918. Score display: 3.195 / 5. Source ID: vals-ai. Evidence capture ID: vals-code-migration-2026-10-15-3fa9c10568ec. Source payload hash: 3fa9c10568ecc117fabec81767c405b49a25d5d2ded308ee435fffb197c53474. Parser version: vals-astro-v3. Imported at: 2026-10-15
- Comparison methodology
- Reasoning effort: max. Maximum output tokens: 128000
Page 1 of 33
Our tests
SVG short test
One SVG prompt and fixed output settings. Captures are shown only with 0 reported reasoning tokens or documented lack of reasoning controls. Identical test conditions do not make the models' internal compute identical.
Earlier tests
Pelican on a bicycle
A community classic for free-form SVG drawing.
GPT-5.6 Luna
Reasoning (requested): high
Current attempt
- Run date
- Sep 7, 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.
Prompt and test conditions
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)Popularity
46.8 / 100
Specifications and access
| Specification | Value and source |
|---|---|
| Weights | ProprietarySource |
| Access | APISource |
| Context window | 1,050,000 tokensSource |
| Knowledge cutoff | February 16, 2026Source |
| Notes | Fast and cheapest tier of the GPT-5.6 family. Generally available from 2026-07-09. Effort-selectable on ChatGPT Work and Codex for Plus, Pro, Business, and Enterprise users. $1 input / $6 output per 1M tokens. Terminal-Bench 2.1 84.3%.Source |
| API model ID | gpt-5.6-lunaSource |
| Maximum output | 128,000 tokensSource |
| Knowledge cutoff | 2026-02-16Source |
| Input | Text, ImageSource |
| Output | TextSource |
| Reasoning mode | none, low, medium, high, xhigh, maxSource |
| API interfaces | Responses API, Chat Completions APISource |
| Tool calling | YesSource |
| Structured output | YesSource |
| Release | 2026-07-09Source |
Published prices
- API input
- $0.2 per 1M tokensSource
- API input
- $0.4 per 1M tokens (above 272,000 context tokens)Source
- API output
- $1.2 per 1M tokensSource
- API output
- $1.8 per 1M tokens (above 272,000 context tokens)Source
- Cache write
- $0.25 per 1M tokensSource
- Cache write
- $0.5 per 1M tokens (above 272,000 context tokens)Source
- Cache read
- $0.02 per 1M tokensSource
- Cache read
- $0.04 per 1M tokens (above 272,000 context tokens)Source