GPT-5.6 Luna
OpenAI · Proprietary · rank 38 · bench-align-v5
Canonical idgpt-5-6-luna
Access typeProprietary
Blended $/1M$0.4575% input / 25% output
Capability shape
Seven axes from the ranking source. A missing axis is drawn as a gap.
Runtime service evidence
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: ObservedUnavailable
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | Unavailable | Unavailable | Unavailable | |
| Throughput | Unavailable | Unavailable | Unavailable |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
Endpoint and price matrix
Every published price component, including cache reads and writes.
| Component | USD | Evidence |
|---|---|---|
| Input / 1M tokens | $0.20 | |
| Output / 1M tokens | $1.20 | |
| Cache read / 1M tokens | $0.02 | |
| Cache write / 1M tokens | Unavailable | |
| Blended / 1M (75% input / 25% output) | $0.45 |
Self-hosted listingOpenAI's API pricing page lists GPT-5.6 Luna at $0.20 input / $0.02 cached input / $1.20 output per million tokens for short-context requests. Prompts above 272K input tokens use the published $0.40 input / $0.04 cached input / $1.80 output long-context tier; cache writes cost $0.25 per million tokens. Observed September 11, 2026; the $1.00 / $6.00 launch rate is retained in the price history.The rates above are a hosted price matched from another provider, not a first-party list price.
Workload-aware monthly cost example
10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
Benchmark record
51 matched benchmark rows with their published value, unit, and provenance.
Knowledge
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| GPQA Graduate-Level Google-Proof Q&A | 92.3 | 448 questions | Graduate level | GPQA: A Graduate-Level Google-Proof Q&A Benchmark |
| GPQA-D GPQA Diamond | 92.3 | Graduate-level science questions | Graduate level | Trinity-Large-Thinking: Scaling an Open Source Frontier Agent |
| Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index | 51.2 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-GPQA Diamond Artificial Analysis GPQA Diamond | 91.1 | Graduate-level science questions | Graduate-level science reasoning | Artificial Analysis GPQA Diamond Benchmark Leaderboard |
| AA-HLE Artificial Analysis Humanity's Last Exam | 39.5 | Expert-level questions | Frontier expert reasoning | Artificial Analysis Humanity's Last Exam Benchmark Leaderboard |
| AA-Omniscience Index Artificial Analysis Omniscience Index | -10.3 | Knowledge questions | Broad factual knowledge | AA-Omniscience: Knowledge and Hallucination Benchmark |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 42.7 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 92.6 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| HealthBench Hard HealthBench Hard | 32.0 | 1,000 health prompts | Advanced health reasoning | Muse Spark Eval Methodology |
| HealthBench Professional HealthBench Professional | 55.7 | Clinician chat tasks | Professional clinical workflows | HealthBench Professional: Evaluating Large Language Models on Real Clinician Chats |
| GPQA Diamond (Vals) GPQA Diamond, Vals AI run | 91.7 | Graduate-level science questions | Expert reasoning | Vals AI GPQA Diamond, Vals AI run leaderboard |
| MMLU-Pro (Vals) MMLU-Pro, Vals AI run | 86.0 | Academic multiple-choice questions | Broad academic knowledge | Vals AI MMLU-Pro, Vals AI run leaderboard |
Coding
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| Terminal-Bench 2.0 Terminal-Bench 2.0 | 84.7 | Terminal-based software tasks | Professional software engineering | Terminal-Bench 2.0 |
| SWE-bench Pro SWE-bench Pro | 62.7 | 1,865 repository problems | Long-horizon professional engineering | SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks? |
| VulcanBench v3 VulcanBench v3 | 85.5 | 23 post-cutoff repository tasks in the v3 report | Professional multi-file software engineering | VulcanBench |
| FrontierCode 1.1 Extended FrontierCode 1.1 Extended | 55.1 | 150 private software-engineering tasks | Frontier coding-agent quality | GPT-5.6 models are now available in Devin |
| AA Coding Index Artificial Analysis Coding Index | 71.5 | Cross-benchmark coding index | Display-only external reference | Artificial Analysis model leaderboards |
| AA-SciCode Artificial Analysis SciCode | 53.6 | Scientific coding subproblems | Scientific programming | Artificial Analysis SciCode Benchmark Leaderboard |
| SWE-bench (Vals) SWE-bench, Vals AI run | 93.0 | Real repository issues by human time bucket | Frontier coding agents | Vals AI SWE-bench, Vals AI run leaderboard |
| DeepSWE DeepSWE | 67.2 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | DeepSWE benchmark blog |
Mathematics
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| FrontierMath (legacy) FrontierMath legacy aggregate | 78.6 | Historical aggregate | Research-level mathematics | FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI |
| FrontierMath v2 (Tiers 1-3) FrontierMath v2 Tiers 1-3 | 78.600 | 295 private advanced mathematics problems | From olympiad-plus to early research mathematics | FrontierMath v2 benchmark hub |
| FrontierMath v2 (Tier 4) FrontierMath v2 Tier 4 | 58.500 | 43 private extreme-difficulty mathematics problems | Research-level mathematics requiring hours or days of expert work | FrontierMath Tier 4 v2 leaderboard |
Reasoning
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| ARC-AGI-2 Abstraction and Reasoning Corpus for AGI v2 | 59.54 | Visual pattern completion and abstract reasoning | Expert-level — hardest public reasoning benchmark | ARC-AGI-2: A Harder General Intelligence Benchmark |
| ARC-AGI-3 Abstraction and Reasoning Corpus for AGI v3 | 0.18 | Interactive game-like tasks with hidden rules | Frontier agentic reasoning | ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence |
| AA-LCR Artificial Analysis Long Context Reasoning | 83.7 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
| MLCR-AA Medical Long Context Reasoning (MLCR-AA) | 19.4 | Long, fragmented medical-record reasoning | Long-context medical reasoning | Medical Long Context Reasoning (MLCR-AA) |
| CritPt Critical Physics Tasks | 20.6 | Research-level physics questions | Research-level physics reasoning | CritPt Benchmark Leaderboard |
Agentic
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| Terminal-Bench 3.0 Terminal-Bench 3.0 | 14.3 | 74 professional computer-work tasks across 7 domains | Frontier autonomous knowledge work | Terminal-Bench 3.0 |
| AA Briefcase Artificial Analysis Briefcase | 1333 | Professional knowledge-work tasks | Professional work | Artificial Analysis Briefcase Benchmark Leaderboard |
| AA EnterpriseOps-Gym Artificial Analysis EnterpriseOps-Gym | 40.8 | Enterprise operations workflows | Enterprise agent operations | Artificial Analysis EnterpriseOps-Gym Benchmark Leaderboard |
| AA Harvey LAB Artificial Analysis Harvey LAB-AA | 87.9 | Legal agent tasks | Professional legal work | Artificial Analysis Harvey LAB-AA Benchmark Leaderboard |
| AA ITBench Artificial Analysis ITBench-AA | 40.3 | IT incident-response tasks | Enterprise IT operations | Artificial Analysis ITBench-AA Benchmark Leaderboard |
| Terminal-Bench 2.0 Terminal-Bench 2.0 | 84.7 | Terminal-based software tasks | Professional software engineering | Terminal-Bench 2.0 |
| BrowseComp BrowseComp | 83.3 | Research questions requiring browsing | Hard web research | BrowseComp |
| GDPval-AA GDPval-AA | 1582 | Agentic real-world work tasks | Professional agentic workflows | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA normalized | 48.2 | Economically valuable tasks | Professional agentic workflows | Artificial Analysis model benchmarks |
| AA Agentic Index Artificial Analysis Agentic Index | 42.7 | Cross-benchmark agentic index | Display-only external reference | Artificial Analysis model leaderboards |
| AA Terminal-Bench 4.0 Artificial Analysis Terminal-Bench v4.0 | 11.6 | Terminal-based agent tasks | Agentic software engineering | Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard |
| GDP.pdf Artificial Analysis GDP.pdf | 24.0 | Professional document-production tasks | Professional knowledge work | GDP.pdf Benchmark Leaderboard |
| APEX-Agents-AA APEX-Agents-AA | 35.8 | 452 professional-services agent tasks | Long-horizon workplace agent tasks | APEX-Agents-AA Benchmark Leaderboard |
| OSWorld 2.0 OSWorld 2.0 | 45.6 | 108 long-horizon computer-use workflows | Long-horizon professional workflows | OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks |
| CyberGym CyberGym | 77.9 | 1,507 vulnerability analysis instances | Real-world cybersecurity | CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale |
| ExploitGym ExploitGym | 12.4 | 898 exploitation tasks | Advanced cybersecurity exploitation | ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks? |
| Toolathlon Toolathlon | 53.4 | Multi-tool workflows | Advanced tool use | Introducing GPT-5.4 mini and nano |
| Terminal-Bench 2.1 (Vals) Terminal-Bench 2.1, Vals AI run | 79.0 | Difficult terminal tasks | Frontier agentic | Vals AI Terminal-Bench 2.1, Vals AI run leaderboard |
| ApprenticeBench ApprenticeBench: end-to-end computer use, continual learning, and long-horizon agency on a real accounts-payable job | 7 | 100 vendor bills processed in sequence inside a simulated construction company | Long-horizon computer use with offline and online continual learning | ApprenticeBench: a step change in AI's job readiness |
Multimodal & Grounded
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| MMMU-Pro Massive Multi-discipline Multimodal Understanding Pro | 78.4 | Multimodal academic reasoning | Frontier multimodal | MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark |
| AA-MMMU-Pro Artificial Analysis MMMU-Pro | 78.6 | Multimodal academic reasoning | Frontier multimodal | Artificial Analysis MMMU-Pro Benchmark Leaderboard |
| MMMU-Pro w/ Python MMMU-Pro with Python | 79.5 | Multimodal academic reasoning | Frontier multimodal | Introducing GPT-5.4 mini and nano |
external
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| ExploitBench ExploitBench v8-bench | 33 | V8 exploit synthesis runs | Browser exploitation and cybersecurity | ExploitBench |
Lifecycle and limitations log
Lifecycle events the source associates with this model, plus what this profile does not claim.
No lifecycle event references this model.
That is not evidence the model has no lifecycle plan — only that this source published none.
What this profile does not claimValues are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned — the attempt timestamp is in each badge. Last attempted fetch for this model’s score: 2026-09-17 17:17 UTC.