OpenAI model product
GPT-5.6-Luna
6 family, designed for cost-sensitive, high-volume workloads.
Updated Aug 17, 2026. Default version: GPT-5.6 Luna
LLMBoard Score76.8GPT-5.6 Luna
Coverage80%44 benchmark families
Context window1.1MTokens
Official input price$0.20OpenAI API
GPT-5.6-Luna Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-5.6-Luna Benchmark Results
Benchmark scores for GPT-5.6 Luna.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkBenchCAD | Score63.1% | Rank02 | Participants4 | Percentile66.7% | EvidenceC | Evaluated |
| BenchmarkGraphwalks BFS >128k | Score81.3% | Rank02 | Participants11 | Percentile90.0% | EvidenceC | Evaluated |
| BenchmarkHealthBench Consensus | Score95.1% | Rank02 | Participants4 | Percentile66.7% | EvidenceC | Evaluated |
| BenchmarkBenchCAD (with Python tool) | Score73.9% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkBig Finance Bench | Score36.0% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkCapture-the-Flag Challenges (Internal) | Score85.2% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkConnectors | Score99.9% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkFrontierMath | Score78.6% | Rank03 | Participants17 | Percentile87.5% | EvidenceC | Evaluated |
| BenchmarkFrontierMath Tier 4 (v2) | Score58.5% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkGeneBench-Pro | Score10.8% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkGraphwalks BFS 1M | Score51.2% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkInternal Research Debugging Evaluation | Score50.8% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkKernelGen 1P | Score22.4% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkLifeSciBench | Score51.2% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkManagement Consulting Tasks (Internal) | Score35.4% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkMedChemBench (Internal) | Score30.4% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkMRCR v2 (8-needle, 512K-1M) | Score41.3% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkNanoGPT | Score1.7% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkPostTrainBench Lite | Score29.6% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkRSI Index | Score41.9% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkSearch and Function-Calling | Score89.7% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkSEC-bench Pro | Score48.9% | Rank03 | Participants3 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkAgents' Last Exam | Score50.3% | Rank04 | Participants10 | Percentile66.7% | EvidenceC | Evaluated |
| BenchmarkARC-AGI-3 | Score0.2% | Rank04 | Participants4 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkDeepSWE | Score67.2% | Rank04 | Participants11 | Percentile70.0% | EvidenceC | Evaluated |
| BenchmarkExploitGym | Score12.4% | Rank04 | Participants4 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkHealthBench Hard | Score32.0% | Rank04 | Participants9 | Percentile62.5% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro (with tools) | Score79.5% | Rank04 | Participants4 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkArtificial Analysis | Score51.0% | Rank05 | Participants7 | Percentile33.3% | EvidenceB | Evaluated |
| BenchmarkExploitBench | Score33.2% | Rank05 | Participants5 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkOSWorld 2.0 | Score45.6% | Rank05 | Participants5 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkGDP.pdf | Score22.7% | Rank06 | Participants6 | Percentile0.0% | EvidenceC | Evaluated |
| BenchmarkHealthBench | Score55.8% | Rank06 | Participants9 | Percentile37.5% | EvidenceC | Evaluated |
| BenchmarkDeepSWE 1.1 | Score67.0% | Rank07 | Participants25 | Percentile75.0% | EvidenceB | Evaluated |
| BenchmarkHealthBench Professional | Score55.7% | Rank07 | Participants9 | Percentile25.0% | EvidenceC | Evaluated |
| BenchmarkTerminal-Bench 2.1 | Score84.7% | Rank08 | Participants28 | Percentile74.1% | EvidenceC | Evaluated |
| BenchmarkFrontierCode 1.1 | Score39.8% | Rank10 | Participants16 | Percentile40.0% | EvidenceB | Evaluated |
| BenchmarkSWE-Bench Pro | Score62.7% | Rank10 | Participants50 | Percentile81.6% | EvidenceC | Evaluated |
| BenchmarkAutomationBench | Score14.9% | Rank11 | Participants12 | Percentile9.1% | EvidenceC | Evaluated |
| BenchmarkMRCR v2 (8-needle) | Score41.3% | Rank12 | Participants23 | Percentile50.0% | EvidenceC | Evaluated |
| BenchmarkToolathlon | Score53.4% | Rank14 | Participants37 | Percentile63.9% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score92.3% | Rank15 | Participants239 | Percentile94.1% | EvidenceC | Evaluated |
| BenchmarkBrowseComp | Score83.3% | Rank18 | Participants62 | Percentile72.1% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro | Score78.4% | Rank20 | Participants68 | Percentile71.6% | EvidenceC | Evaluated |
GPT-5.6-Luna Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenaagent bash recovery steps | Categoryoverall | Rank08 | Rating / score0.1 | VotesN/A | Observations12.5K | Result date |
| Arenaagent tool hallucination | Categoryoverall | Rank09 | Rating / score0.0 | VotesN/A | Observations496.9K | Result date |
| Arenaagent praise complaint | Categoryoverall | Rank16 | Rating / score0.1 | VotesN/A | Observations2.4K | Result date |
| Arenadocument style control | Categoryoverall | Rank17 | Rating / score1466.7 | Votes1,888 | ObservationsN/A | Result date |
| Arenaagent | Categoryoverall | Rank18 | Rating / score0.0 | VotesN/A | Observations528.2K | Result date |
| Arenadocument | Categoryoverall | Rank18 | Rating / score1462.3 | Votes1,888 | ObservationsN/A | Result date |
| Arenaagent steerability | Categoryoverall | Rank25 | Rating / score0.0 | VotesN/A | Observations9.9K | Result date |
| Arenawebdev | Categoryoverall | Rank28 | Rating / score1516.7 | Votes5,066 | ObservationsN/A | Result date |
| Arenaagent task outcome explicit | Categoryoverall | Rank31 | Rating / score-0.0 | VotesN/A | Observations6.4K | Result date |
| Arenavision style control | Categoryoverall | Rank40 | Rating / score1249.3 | Votes3,259 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryoverall | Rank42 | Rating / score1455.3 | Votes16,387 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank45 | Rating / score1251.5 | Votes3,259 | ObservationsN/A | Result date |
| Arenatext style control | Categoryoverall | Rank60 | Rating / score1450.6 | Votes16,419 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank80 | Rating / score1428.3 | Votes16,419 | ObservationsN/A | Result date |
GPT-5.6-Luna Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.20 input, $1.2 output per 1M
- Official provider
- OpenAI
- Lowest third-party
- From $0.10 input, $0.60 output per 1M via NanoGPT
- Tracked offerings
- 32
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderKenari | Provider model IDgpt-5-6-luna | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context1.1M | Updated |
| ProviderNanoGPT | Provider model IDopenai/gpt-5.6-luna | Regionglobal | Input / 1M$0.10 | Output / 1M$0.60 | Context1.1M | Updated |
| ProviderOpenRouter | Provider model IDopenai/gpt-5.6-luna | Regionglobal | Input / 1M$0.10 | Output / 1M$0.60 | Context1.1M | Updated |
| ProviderOpenCode Go | Provider model IDgpt-5.6-luna | Regionglobal | Input / 1M$0.10 | Output / 1M$0.60 | Context1.1M | Updated |
| ProviderImpossibl | Provider model IDopenai/gpt-5.6-luna | Regionglobal | Input / 1M$0.20 | Output / 1M$1.2 | Context1.1M | Updated |
| ProviderCrossModel | Provider model IDopenai/gpt-5.6-luna | Regionglobal | Input / 1M$0.20 | Output / 1M$1.2 | Context1.1M | Updated |
| ProviderOpenAI | Provider model IDgpt-5.6-luna | Regionglobal | Input / 1M$0.20 | Output / 1M$1.2 | Context1.1M | Updated |
| ProviderMerge Gateway | Provider model IDopenai/gpt-5.6-luna | Regionglobal | Input / 1M$0.20 | Output / 1M$1.2 | Context1.1M | Updated |
| ProviderCloudflare AI Gateway | Provider model IDopenai/gpt-5.6-luna | Regionglobal | Input / 1M$0.20 | Output / 1M$1.2 | Context1.1M | Updated |
| ProviderOfox | Provider model IDopenai/gpt-5.6-luna | Regionglobal | Input / 1M$0.20 | Output / 1M$1.2 | Context1.1M | Updated |
| ProviderOpenCode Zen | Provider model IDgpt-5.6-luna | Regionglobal | Input / 1M$0.20 | Output / 1M$1.2 | Context1.1M | Updated |
| ProviderAzure | Provider model IDgpt-5.6-luna | Regionglobal | Input / 1M$0.20 | Output / 1M$1.2 | Context1.1M | Updated |
| ProviderVercel AI Gateway | Provider model IDopenai/gpt-5.6-luna | Regionglobal | Input / 1M$0.20 | Output / 1M$1.2 | Context1.1M | Updated |
| ProviderEden AI | Provider model IDopenai/gpt-5.6-luna | Regionglobal | Input / 1M$0.20 | Output / 1M$1.2 | Context1.1M | Updated |
| ProviderLLM Gateway | Provider model IDgpt-5.6-luna | Regionglobal | Input / 1M$0.20 | Output / 1M$1.2 | Context1.1M | Updated |
| ProviderGitHub Copilot | Provider model IDgpt-5.6-luna | Regionglobal | Input / 1M$0.20 | Output / 1M$1.2 | Context1.1M | Updated |
| ProviderKilo Gateway | Provider model IDopenai/gpt-5.6-luna | Regionglobal | Input / 1M$0.20 | Output / 1M$1.2 | Context1.1M | Updated |
| ProviderKilo Gateway | Provider model IDopenai/gpt-5.6-luna-pro | Regionglobal | Input / 1M$0.20 | Output / 1M$1.2 | Context1.1M | Updated |
| ProviderAmazon Bedrock | Provider model IDopenai.gpt-5.6-luna | Regionglobal | Input / 1M$0.22 | Output / 1M$1.32 | Context1.1M | Updated |
| ProviderVenice AI | Provider model IDopenai-gpt-56-luna | Regionglobal | Input / 1M$0.2667 | Output / 1M$1.6 | Context1M | Updated |
| Providerrouting.run | Provider model IDgpt-5.6-luna | Regionglobal | Input / 1M$0.70 | Output / 1M$4.2 | Context1M | Updated |
| ProviderAI-ROUTER | Provider model IDgpt-5.6-luna | Regionglobal | Input / 1M$1 | Output / 1M$6 | Context1.1M | Updated |
| ProviderDatabricks | Provider model IDdatabricks-gpt-5-6-luna | Regionglobal | Input / 1M$1 | Output / 1M$6 | Context400K | Updated |
| ProviderVivgrid | Provider model IDgpt-5.6-luna | Regionglobal | Input / 1M$1 | Output / 1M$6 | Context1.1M | Updated |
| ProviderZenMux | Provider model IDopenai/gpt-5.6-luna | Regionglobal | Input / 1M$1 | Output / 1M$6 | Context1.1M | Updated |
| ProviderNeon | Provider model IDgpt-5-6-luna | Regionglobal | Input / 1M$1 | Output / 1M$6 | Context1.1M | Updated |
| ProviderAzure Cognitive Services | Provider model IDgpt-5.6-luna | Regionglobal | Input / 1M$1 | Output / 1M$6 | Context1.1M | Updated |
| ProviderAIHubMix | Provider model IDgpt-5.6-luna | Regionglobal | Input / 1M$1 | Output / 1M$6 | Context1.1M | Updated |
| ProviderPioneer | Provider model IDgpt-5.6-luna | Regionglobal | Input / 1M$1 | Output / 1M$6 | Context1.1M | Updated |
| ProviderAbacus | Provider model IDgpt-5.6-luna | Regionglobal | Input / 1M$1 | Output / 1M$6 | Context1M | Updated |
| ProviderCortecs | Provider model IDgpt-5.6-luna | Regionglobal | Input / 1M$1.1 | Output / 1M$6.6 | Context1.1M | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
GPT-5.6-Luna Runtime Performance
Provider-specific output speed and catalog latency for GPT-5.6 Luna. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderOpenAI | Output Speed48.852 tok/s | Catalog Latency5.239 s | Max Input1.1M | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GPT-5.6-Luna Specifications
Technical details for the model's default version.
- Version
- GPT-5.6 Luna
- Released
- Jul 9, 2026
- Knowledge cutoff
- Feb 16, 2026
- Parameters
- N/A
- Context window
- 1.1M
- Max output
- 128K
- Inputs
- image, pdf, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
GPT-5.6-Luna Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGPT-5.6 Luna | Released | LLMBoard76.8 | ParametersN/A | Context1.1M | Max output128K | Open weightsNo | LicenseProprietary |
GPT-5.6-Luna vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to GPT-5.6-Luna
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-5.4
OpenAI
OP
GPT-5.5-Pro
OpenAI
OP
GPT-5.2-Pro
OpenAI
OP
GPT-5.2
OpenAI
OP
GPT-5.5
OpenAI
OP
GPT-5.6-Terra
OpenAI
What is GPT-5.6-Luna?
Key information about GPT-5.6-Luna and its available data.
6 family, designed for cost-sensitive, high-volume workloads. 05M-token context window.
Data as of 2026-08-17.
FAQ
Common questions about GPT-5.6-Luna.
When was GPT-5.6-Luna released?
GPT-5.6-Luna's default version was released on Jul 9, 2026.
How much does GPT-5.6-Luna cost?
GPT-5.6-Luna's official API price is $0.20 per million input tokens and $1.2 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $0.10 input and $0.60 output via NanoGPT.
Who created GPT-5.6-Luna?
GPT-5.6-Luna was created by OpenAI.
What is the context window for GPT-5.6-Luna?
The default version has a 1.1M token context window.
Is GPT-5.6-Luna open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-5.6-Luna?
32 provider offerings are linked to the default version.
What models should I compare GPT-5.6-Luna with?
Nearby ranked alternatives include Qwen3.8 27B, Gemini 3.1 Pro, DeepSeek-V4-Flash.