OpenAIGPT-6 Luna
No cheaper ranked model scores higher: it is on the price frontier.
As of 9 Nov 2026, GPT-6 Luna by OpenAI scores 56.5 on the BenchLeader Index (599 ranked configurations), with its best results in long context (66) and weakest in knowledge (45). API pricing: $0.100 per 1M input tokens and $0.500 per 1M output tokens ($0.200 blended at 3:1), list price on 9 Nov 2026. It streams about 100 tokens/s (Artificial Analysis). Released 22 Sep 2026.
Key facts (as of 9 Nov 2026)
- GPT-6 Luna API pricing: $0.100 per 1M input tokens and $0.500 per 1M output tokens ($0.200 blended at 3:1) (list price, 9 Nov 2026).
- GPT-6 Luna streams about 100 tokens/s (Artificial Analysis, 9 Nov 2026).
- GPT-6 Luna was released on 22 Sep 2026 (OpenAI).
In detail. GPT-6 Luna is an OpenAI proprietary reasoning model, released 22 Sep 2026. Its best configuration (max reasoning effort) ranks #177 of 599 on the BenchLeader Index at 56.5 ±3.2, in the upper half. The ± is the point: 244 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in long context (66) and lowest in knowledge (45). At $0.200 per million tokens blended it is among the cheapest fifth of ranked models. Output speed of 104 tokens per second puts it faster than most, with a first answer in 85.0 s. It has been measured at 8 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 8 Nov 2026.
- Blended price
- $0.200/M
- $0.100 in · $0.500 out
- via Artificial Analysis
- Output speed
- 104 tok/s
- measured by Artificial Analysis
- First answer
- 85 s
- first token 2.39 s
- Context
- 1.1M
- via models.dev
- Full answer
- 177 s
- median, reasoning included
- Cost per task
- $0.152
- 12 min a task, AA Index
- Tokens per task
- 75k
- 76% of it reasoning
- Released
- 22 Sep 2026
- Overall index57
- Reasoning56
- Coding58
- Agents & tools49
- Maths64
- Knowledge45
- Human preference62
- Multimodal58
- Long context66
Versions
OpenAI has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| GPT-6 Lunamaxthis page | 22 Sep 2026 | 56.5 | #177 |
| GPT-5.6 Lunaxhigh | 9 Jul 2026 | 58.4 | #129 |
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| no reasoning | 40.0 | #525 | 83 tok/s | 1.19 s | $0.0002 | Coding 34 · Knowledge 31 · Long context 44 · Multimodal 44 · Reasoning 33 |
| low | 45.8 | #434 | 90 tok/s | 2.48 s | $0.0002 | Agents & tools 41 · Coding 37 · Knowledge 35 · Long context 62 · Multimodal 58 · Reasoning 36 |
| medium | 49.7 | #350 | 99 tok/s | 5.16 s | $0.0002 | Agents & tools 48 · Coding 46 · Knowledge 37 · Long context 64 · Multimodal 60 · Reasoning 43 |
| high | 51.2 | #316 | 98 tok/s | 11 s | $0.0002 | Coding 50 · Knowledge 38 · Long context 64 · Multimodal 60 · Reasoning 46 |
| xhigh | 52.1 | #287 | 102 tok/s | 22 s | $0.0002 | Coding 50 · Knowledge 38 · Long context 65 · Multimodal 62 · Reasoning 49 |
| maxbest | 56.5 | #177 | 104 tok/s | 85 s | $0.0002 | Agents & tools 49 · Coding 58 · Human preference 62 · Knowledge 45 · Long context 66 · Maths 64 · Multimodal 58 · Reasoning 56 |
| pro mode | – | – | 70 tok/s | 2.39 s | $0.0002 | |
| not stated | – | – | 70 tok/s | 2.39 s | $0.0002 | Composite 46 · Knowledge 46 · Maths 61 |
What more thinking costs
Turning the effort up buys index points and multiplies the bill. Here max costs 30× low for +10.7 on the index — 2.2 points per doubling of spend. Compare that with other models.
Each point is one reasoning setting: its cost per Artificial Analysis index task (log scale) and its BenchLeader Index.
How its index has moved
23 Sep 2026 to 9 Nov 2026- max
- xhigh
- high
- medium
The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | no reasoning | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| GPQA Diamond | – | – | – | – | – | 90.5%#47 | – | Epoch AI Benchmarking Hub | |
| Arena Hard Prompts | – | – | – | – | – | 1463#91 | – | Arena (LMArena) | |
| LiveBench 2.0 Reasoningnot in indexeffort not stated | – | – | – | – | – | – | 81.8%#23 | LiveBench | |
| LiveBench 1.0 Reasoningnot in index | – | – | – | – | – | 81.8%#49 | – | LiveBench | |
| Humanity's Last Exam (AA)not in index | 8.6%#366 | 20.3%#230 | 28.3%#179 | 33.0%#153 | 34.3%#140 | 38.5%#108 | – | Artificial Analysis | |
| HLE-Diamond (AA) | 6.3%#131 | 10.2%#113 | 15.1%#94 | 15.6%#91 | 18.9%#78 | 22.2%#68 | – | Artificial Analysis | |
| ARC-AGI-1 | 8.8%#244 | 37.7%#204 | 61.0%#166 | 70.3%#149 | 73.0%#144 | 86.7%#108 | – | ARC Prize | |
| ARC-AGI-2 | 0.0%#250 | 4.6%#189 | 18.1%#154 | 31.4%#137 | 41.9%#124 | 59.3%#98 | – | ARC Prize | |
| ARC-AGI-3 | 0.0%#74 | 0.2%#65 | 0.3%#60 | 0.4%#56 | 0.5%#52 | 0.6%#50 | – | ARC Prize | |
| CritPtnot in index | 1.1%#240 | 2.6%#206 | 10.6%#129 | 15.4%#98 | 17.4%#88 | 19.4%#75 | – | Artificial Analysis | |
| CritPt v2 hard subset (AA) | 5.0%#106 | 9.5%#100 | 27.5%#78 | 31.0%#71 | 37.0%#59 | 42.5%#52 | – | Artificial Analysis | |
| MysteryMechanismnot in index | – | – | – | – | – | 19.4%#26 | – | Vals AI | |
| Chess Puzzlesnot in index | – | – | – | – | – | 36.0%#51 | – | Epoch AI Benchmarking Hub | |
| Mystery Game Puzzlesnot in index | – | – | – | – | – | 7.0%#126 | – | Epoch AI Benchmarking Hub | |
| LMCAnot in index | – | – | – | – | – | 44.5%#93 | – | Epoch AI Benchmarking Hub | |
| DTBenchnot in index | – | – | – | – | – | 90.1%#82 | – | Epoch AI Benchmarking Hub |
Coding
| Benchmark | no reasoning | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| SciCode | 43.1%#156 | 46.9%#139 | 50.9%#109 | 50.4%#113 | 51.7%#97 | 54.6%#63 | – | SciCode | |
| FrontierCode | – | – | – | – | – | 42.4%#22 | – | Cognition | |
| Arena Coding | – | – | – | – | – | 1502#78 | – | Arena (LMArena) | |
| Arena WebDev | – | – | – | – | – | 1577#41 | – | Arena (LMArena) | |
| LiveBench 2.0 Codingnot in indexeffort not stated | – | – | – | – | – | – | 70.8%#18 | LiveBench | |
| LiveBench 1.0 Codingnot in index | – | – | – | – | – | 79.0%#26 | – | LiveBench | |
| SciCode (AA)not in index | 43.1%#171 | 46.9%#151 | 50.9%#113 | 50.4%#119 | 51.7%#101 | 54.6%#69 | – | Artificial Analysis | |
| IOI | – | – | – | – | – | 55.6%#22 | – | Vals AI | |
| Code Migrationnot in index | – | – | – | – | – | 42.5%#28 | – | Vals AI | |
| Code Migration v1.1not in index | – | – | – | – | – | 46.7%#19 | – | Vals AI | |
| ProgramBenchnot in index | – | – | – | – | – | 0.5%#19 | – | Vals AI | |
| SWE-bench Multimodalnot in index | – | – | – | – | – | 37.5%#20 | – | Vals AI | |
| Vibe Code Bench v1.1not in index | – | – | – | – | – | 81.7%#28 | – | Vals AI | |
| MirrorCodenot in index | – | – | – | – | – | 26.7%#10 | – | Epoch AI Benchmarking Hub | |
| ALE-Benchnot in index | – | – | – | – | 1576.9#24 | – | – | Epoch AI Benchmarking Hub | |
| Terminal-Bench 4.0 (AA)not in index | 1.5%#147 | 0.0%#179 | 2.5%#138 | 4.5%#130 | 8.1%#118 | 12.6%#102 | – | Artificial Analysis | |
| Startrise Frontendnot in indexeffort not stated | – | – | – | – | – | – | 69.3%#27 | Startrise | |
| GameBench 2 Overallnot in indexacross settings | – | – | – | – | – | – | 47.1#34 | DuelLab GameBench 2 | |
| GameBench 2 by reasoning settingnot in index | 43.5#106 | – | 41.9#115 | – | 55.8#63 | – | – | DuelLab GameBench 2 | |
| Design Arena Websitenot in indexeffort not stated | – | – | – | – | – | – | 1265#44 | Design Arena | |
| FrontierCode 1.1 (AA)not in index | 13.8%#77 | 14.1%#75 | 31.8%#63 | 32.0%#62 | 33.2%#60 | 41.9%#33 | – | Artificial Analysis | |
| FrontierCode 2.0 (AA) | 1.6%#106 | 2.2%#104 | 12.8%#82 | 18.6%#66 | 18.4%#67 | 25.2%#49 | – | Artificial Analysis |
Agents & tools
| Benchmark | no reasoning | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| Terminal-Bench | – | – | – | – | – | 15.2%#78 | – | Terminal-Bench | |
| APEX-Agents | – | – | – | – | – | 44.3%#44 | – | Mercor | |
| Arena Agent | – | -6.2#42 | -2#34 | – | – | 1.5#23 | – | Arena (LMArena) | |
| LiveBench Long Agenticnot in indexeffort not stated | – | – | – | – | – | – | 24.7%#20 | LiveBench | |
| LiveBench Browsernot in indexeffort not stated | – | – | – | – | – | – | 70.3%#13 | LiveBench | |
| LiveBench Agentic Codingnot in index | – | – | – | – | – | 51.2%#41 | – | LiveBench | |
| Terminal-Bench 2.1 (Vals) | – | – | – | – | – | 73.0%#23 | – | Vals AI | |
| GDPval-AA v2.1, normalised scorenot in index | 27.2%#90 | 26.6%#92 | 38.1%#67 | 42.1%#58 | 43.2%#55 | 46.6%#46 | – | Artificial Analysis | |
| GDPval-AA v2.1not in index | 1052#94 | 1040#96 | 1270#70 | 1352#60 | 1373#56 | 1444#48 | – | Artificial Analysis | |
| Analyst Agent (AA)not in index | – | – | – | – | – | 43.8%#21 | – | Artificial Analysis | |
| CyberBenchnot in index | – | – | – | – | – | 76.3%#5 | – | Vals AI | |
| Finance Agent v2not in index | – | – | – | – | – | 49.9%#46 | – | Vals AI | |
| Finance Agent v2.1not in index | – | – | – | – | – | 56.8%#31 | – | Vals AI | |
| Harvey's Legal Agent Benchmark v1.1not in index | – | – | – | – | – | 4.2%#31 | – | Vals AI | |
| Harvey's Legal Agent Benchmark v1not in index | – | – | – | – | – | 2.9%#44 | – | Vals AI | |
| Legal Research Benchnot in index | – | – | – | – | – | 30.3%#55 | – | Vals AI | |
| SREBenchnot in index | – | – | – | – | – | 2.7%#24 | – | Vals AI | |
| Tax Agent Benchnot in index | – | – | – | – | – | 19.9%#55 | – | Vals AI | |
| Terminal-Bench 4.0 (Vals)not in index | – | – | – | – | – | 13.6%#42 | – | Vals AI | |
| Terminal-Bench Sciencenot in index | – | – | – | – | – | 4.3%#27 | – | Vals AI | |
| Arena Searchnot in index | – | – | – | – | – | 1211#12 | – | Arena (LMArena) | |
| AutomationBenchnot in index | 9.1%#181 | 12.1%#178 | 40.5%#123 | 47.8%#108 | 47.8%#110 | 53.2%#88 | – | Artificial Analysis | |
| GDP.pdf (AA)not in index | 5.8%#183 | 9.0%#163 | 13.8%#126 | 18.2%#95 | 18.6%#90 | 22.8%#59 | – | Artificial Analysis | |
| Harvey LAB-AA v1.1not in index | – | – | – | – | – | 3.3%#17 | – | Harvey | |
| AA-Briefcase v1.1not in index | 903#122 | 740#131 | 1096#100 | 1187#91 | 1235#85 | 1337#72 | – | Artificial Analysis | |
| GDPxnot in index | – | – | – | – | – | 5.1%#12 | – | GDPx by SemiAnalysis | |
| Design Arena Agenticnot in indexeffort not stated | – | – | – | – | – | – | 1149#49 | Design Arena | |
| Terminal-Bench-Science 0.1 (AA)not in index | 0.9%#98 | 0.9%#98 | 1.4%#97 | 2.9%#91 | 5.2%#77 | 8.6%#66 | – | Artificial Analysis | |
| CWE-Bench (AA) | – | – | – | – | – | 56.7%#10 | – | Artificial Analysis | |
| DeepSec-Bench (AA) | – | – | – | – | – | 23.5%#11 | – | Artificial Analysis | |
| CyberGym end-to-end (AA) | – | – | – | – | – | 77.9%#5 | – | Artificial Analysis | |
| FACTS Searchnot in indexeffort not stated | – | – | – | – | – | – | 86.8%#9 |
Maths
| Benchmark | max | not stated | Source | Trend |
|---|---|---|---|---|
| FrontierMath Tiers 1–3 | 79.0%#19 | – | Epoch AI Benchmarking Hub | |
| FrontierMath Tier 4 | 56.1%#26 | – | Epoch AI Benchmarking Hub | |
| OTIS Mock AIME | 98.9%#23 | – | Epoch AI Benchmarking Hub | |
| ProofBencheffort not stated | – | 64.0%#20 | Vals AI | |
| LiveBench Mathematicsnot in index | 89.1%#40 | – | LiveBench | |
| Arena Maths | 1450#79 | – | Arena (LMArena) |
Knowledge
| Benchmark | no reasoning | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| SimpleQA Verified | – | – | – | – | – | 41.4%#48 | – | Epoch AI Benchmarking Hub | |
| LiveBench 2.0 Data Analysisnot in indexeffort not stated | – | – | – | – | – | – | 73.4%#20 | LiveBench | |
| LiveBench Researchnot in indexeffort not stated | – | – | – | – | – | – | 48.5%#31 | LiveBench | |
| LiveBench 1.0 Data Analysisnot in index | – | – | – | – | – | 73.4%#42 | – | LiveBench | |
| AA-Omniscience v1.1 | -25.8#122 | -18.1#117 | -13.6#110 | -12.8#108 | -13.0#109 | -8.3#96 | – | Artificial Analysis | |
| PRBench Legaleffort not stated | – | – | – | – | – | – | 42.9%#28 | Scale AI SEAL | |
| BioMysteryBenchnot in index | – | – | – | – | – | 61.5%#27 | – | Vals AI | |
| ClaimBenchnot in index | – | – | – | – | – | 99.2%#5 | – | Vals AI | |
| Excel Modeling Benchmarknot in index | – | – | – | – | – | 68.5%#16 | – | Vals AI | |
| Excel Modeling Benchmark v1.1not in index | – | – | – | – | – | 70.0%#18 | – | Vals AI | |
| MedCodenot in index | – | – | – | – | – | 44.7%#41 | – | Vals AI | |
| MedScribenot in index | – | – | – | – | – | 83.7%#43 | – | Vals AI | |
| Public Benefits Bench v1.1not in index | – | – | – | – | – | 57.6%#38 | – | Vals AI | |
| GDP.pdfnot in index | – | – | – | – | – | 23.0%#25 | – | Epoch AI Benchmarking Hub | |
| AA-Omniscience v1.1: accuracynot in index | 30.1%#93 | 36.1%#78 | 38.7%#69 | 39.0%#67 | 38.6%#70 | 39.6%#63 | – | Artificial Analysis | |
| AA-Omniscience v1.1: non-hallucinationnot in index | 20.0%#107 | 15.2%#114 | 14.7%#116 | 15.1%#115 | 16.0%#112 | 20.6%#106 | – | Artificial Analysis | |
| HealthBench Professional (AA)not in index | – | – | – | – | – | 61.9%#10 | – | OpenAI |
Instruction following
| Benchmark | max | Source | Trend |
|---|---|---|---|
| LiveBench Languagenot in index | 73.8%#53 | LiveBench | |
| LiveBench Instruction Followingnot in index | 55.9%#64 | LiveBench | |
| Arena Instruction Followingnot in index | 1436#84 | Arena (LMArena) |
Human preference
| Benchmark | max | Source | Trend |
|---|---|---|---|
| Arena Text | 1441#96 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1407#98 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1442#103 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1448#92 | Arena (LMArena) |
Multimodal
| Benchmark | no reasoning | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| Arena Vision | – | – | – | – | – | 1211#86 | – | Arena (LMArena) | |
| LiveBench Designnot in indexeffort not stated | – | – | – | – | – | – | 76.1%#13 | LiveBench | |
| MMMU-Pro | 62.1%#212 | 76.0%#105 | 77.9%#90 | 77.5%#92 | 79.7%#66 | 79.7%#68 | – | Artificial Analysis | |
| SAGEnot in index | – | – | – | – | – | 83.4%#21 | – | Vals AI | |
| Blueprint-Bench 2not in indexeffort not stated | – | – | – | – | – | – | 31.2%#17 | Epoch AI Benchmarking Hub | |
| Code2Video-AAnot in index | – | – | – | – | – | 1030#14 | – | Artificial Analysis | |
| AA-3Dnot in index | – | – | – | – | – | 1000#12 | – | Artificial Analysis |
Long context
| Benchmark | no reasoning | low | medium | high | xhigh | max | Source | Trend |
|---|---|---|---|---|---|---|---|---|
| AA-LCR v1.1 | 39.7%#381 | 74.0%#183 | 78.3%#126 | 79.3%#110 | 80.0%#88 | 83.3%#22 | Artificial Analysis | |
| MLCRnot in index | 15.0%#81 | 18.9%#58 | 18.3%#62 | 19.4%#54 | 20.6%#46 | 26.1%#27 | Artificial Analysis |
Composite
| Benchmark | no reasoning | low | medium | high | xhigh | max | not stated | Source | Trend |
|---|---|---|---|---|---|---|---|---|---|
| Epoch Capabilities Indexnot in indexeffort not stated | – | – | – | – | – | – | 156.7#32 | Epoch AI Benchmarking Hub | |
| LiveBench 2.0effort not stated | – | – | – | – | – | – | 60.4%#22 | LiveBench | |
| LiveBench 1.0not in index | – | – | – | – | – | 72.0%#51 | – | LiveBench | |
| AA Intelligence Index v5.0not in index | 9.4#104 | 9.7#103 | 18.4#90 | 21.4#84 | 23.4#79 | 27.9#69 | – | Artificial Analysis | |
| AA Intelligence Index v4.3.2not in index | 18.5#262 | 21.5#220 | 29.9#132 | 32.9#115 | 34.6#96 | 38.1#83 | – | Artificial Analysis | |
| AA Progress Index v1not in index | 244.6#277 | 272.7#194 | 299.8#120 | 306.4#106 | 310.3#95 | 317.1#77 | – | Artificial Analysis | |
| Vals Indexnot in index | – | – | – | – | – | 52.3#28 | – | Vals AI | |
| Vals Finance Indexnot in index | – | – | – | – | – | 53.0%#30 | – | Vals AI | |
| Vals Science Indexnot in index | – | – | – | – | – | 28.4%#21 | – | Vals AI | |
| Vals Router Indexnot in indexeffort not stated | – | – | – | – | – | – | 52.3%#19 | Vals AI | |
| AA Cyber Indexnot in index | – | – | – | – | – | 52.7#5 | – | Artificial Analysis |
Safety & honesty
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| FORTRESSnot in index | 10.8%#73 | Scale AI SEAL |
GameBench 2 Overall: 47.1. GameBench 2, best reasoning setting (XHigh): 55.8. Reference only, not part of the BenchLeader Index.
DuelLab GameBench 2, release gb2-20261103-eaea31df94e6 (https://benchmarks.duellab.org/releases/gb2-20261103-eaea31df94e6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
Where it wins
Benchmarks where this configuration ranks in the top five of every configuration measured.
API pricing: where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Amazon Bedrock | 129 tok/s | 1.18 s | $0.100 | $0.500 | 1.1M | – |
| OpenAI | 98 tok/s | 0.89 s | $0.200 | $1.00 | 1.1M | – |
| Amazon Bedrock | 85 tok/s | 1.21 s | $0.110 | $0.550 | 1.1M | – |
| Azure | 77 tok/s | 2.63 s | $0.110 | $0.550 | 1.1M | – |
| Azure | 75 tok/s | 1.10 s | $0.110 | $0.550 | 1.1M | – |
| Azure | 74 tok/s | 3.15 s | $0.100 | $0.500 | 1.1M | – |
| OpenAI | 71 tok/s | 2.58 s | $0.100 | $0.500 | 1.1M | – |
| OpenAI | 54 tok/s | 2.62 s | $0.050 | $0.250 | 1.1M | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.010 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0002 | $0.0002 | 1.5 min |
| Summarize a 30-page report | 12,000 / 600 | $0.0015 | $0.0007 | 1.5 min |
| Code edit | 6,000 / 1,500 | $0.0014 | $0.0009 | 1.7 min |
| Agentic coding session | 60,000 / 4,000 | $0.0080 | $0.0040 | 2.1 min |
| Structured extraction | 2,000 / 200 | $0.0003 | $0.0002 | 1.4 min |
Compare GPT-6 Luna with…
See also
Embed or cite
Show where GPT-6 Luna ranks on a model card or README. The badge redraws itself with every daily update, carries the data date and links back to this page. To see ranks like this on OpenRouter and Hugging Face model pages, get the Chrome extension.
[](https://www.benchleader.com/models/gpt-6-luna)Cite this
The ranking changes daily, so a reference carries the data date. APA style:
BenchLeader. (2026, November 9). GPT-6 Luna on the BenchLeader Index (method v1.4) [Data set]. Retrieved November 9, 2026, from https://www.benchleader.com/models/gpt-6-luna
BibTeX:
@misc{benchleader_gpt_6_luna_20261109,
author = {{BenchLeader}},
title = {{GPT-6 Luna on the BenchLeader Index (method v1.4)}},
year = {2026},
month = nov,
howpublished = {\url{https://www.benchleader.com/models/gpt-6-luna}},
note = {Data as of 2026-11-09}
}Every badge style, the embeddable top-10 widget and how to cite the Index
Questions people ask
- What are GPT-6 Luna's benchmark scores?
- As of 9 Nov 2026, GPT-6 Luna (max effort) scores 56.5 ±3.2 on the BenchLeader Index, strongest in long context (66) and weakest in knowledge (45). That rests on independent benchmark results only, and every score on this page links to its publisher.
- How does GPT-6 Luna rank?
- GPT-6 Luna (max effort) is #177 of 599 ranked configurations on 9 Nov 2026. 244 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Fable 5.2 (max effort) at 69.4.
- How much does GPT-6 Luna cost per 1M tokens?
- As of 9 Nov 2026, GPT-6 Luna costs $0.100 per 1M input tokens and $0.500 per 1M output tokens, $0.200 blended (three input tokens per output token).
- Is GPT-6 Luna better than GPT-5.5?
- As of 9 Nov 2026, GPT-5.5 (xhigh) leads on quality (64.3 vs 56.5 on the BenchLeader Index), but GPT-6 Luna (max) costs 56× less, so it is the better buy unless you need the extra quality. The head-to-head page has the benchmark-by-benchmark detail.
- When was GPT-6 Luna released?
- OpenAI released GPT-6 Luna on 22 Sep 2026. BenchLeader has results for it at 8 reasoning-effort settings.
Data as of 9 Nov 2026. Compare these configurations.
Cite as: BenchLeader, “GPT-6 Luna: benchmarks, pricing, speed and rank”, data as of 9 Nov 2026, https://www.benchleader.com/models/gpt-6-luna.