OpenAI, proprietary

# GPT-5.6 Luna

> GPT-5.6 Luna by OpenAI, released July 2026. Ranked #30 of 354 with a Noometry Index of 54.6. API: $0.20 in / $1.20 out per M tokens. 1.05M context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/gpt-5-6-luna
- Last updated: 2026-10-10
- Title: GPT-5.6 Luna Benchmarks, Price & Rank (October 2026)

GPT-5.6 Luna by OpenAI ranks 30th of 354 ranked models on the Noometry Index as of October 2026, with a score of 54.6. Its strongest category is math, where it ranks 14th. API pricing starts at $0.20 per million input tokens and $1.20 per million output tokens, with a 1.05M-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #30 of 354
- **Index score:** 54.6
- **Evidence:** Confirmed 52 results
- **Provider:** [OpenAI](https://noometry.com/providers/openai)
- **Released:** July 9, 2026
- **Weights:** Proprietary
- **Reasoning:** Yes
- **Context window:** 1.05M
- **Max output:** 128K
- **Input price:** $0.20 / M
- **Output price:** $1.20 / M
- **Blended price:** $0.45 / M
- **Output speed:** 12 tokens/s [Kagi](https://help.kagi.com/kagi/ai/llm-benchmark.html)
- **Value:** #52 of 219
- **Knowledge cutoff:** February 2026
- **Input:** text, image, pdf

## Category scores

Each category score combines every public result we have in that category.

GPT-5.6 Luna category scores

1.  Coding 54.5
2.  Agentic & Tool Use 34.4
3.  Reasoning 47.6
4.  Math 77.7
5.  Knowledge 58.5
6.  Multimodal 42.7
7.  Multilingual 52.8
8.  Instruction Following 75.6
9.  Long Context 43.9
10.  Writing & Preference 68.0
11.  020406080

GPT-5.6 Luna category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 54.5 | #28 | 7 |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 34.4 | #45 | 3 |
| [Reasoning](https://noometry.com/best/reasoning) | 47.6 | #43 | 12 |
| [Math](https://noometry.com/best/math) | 77.7 | #14 | 5 |
| [Knowledge](https://noometry.com/best/knowledge) | 58.5 | #34 | 3 |
| [Multimodal](https://noometry.com/best/multimodal) | 42.7 | #28 | 3 |
| [Multilingual](https://noometry.com/best/multilingual) | 52.8 | #78 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 75.6 | #57 | 1 |
| [Long Context](https://noometry.com/best/long-context) | 43.9 | #82 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 68.0 | #29 | 5 |

## Strengths and weaknesses

Categories where GPT-5.6 Luna places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

GPT-5.6 Luna: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Math](https://noometry.com/best/math) | 77.7 | +41.1 | #14 of 327, top 5% |
| [Coding](https://noometry.com/best/coding) | 54.5 | +15.8 | #28 of 340, top 9% |
| [Writing & Preference](https://noometry.com/best/writing) | 68.0 | +14.2 | #29 of 312, top 10% |

### Weakest categories

GPT-5.6 Luna: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 34.4 | +4.1 | #45 of 154, top 30% |
| [Long Context](https://noometry.com/best/long-context) | 43.9 | +3.0 | #82 of 296, top 28% |
| [Multilingual](https://noometry.com/best/multilingual) | 52.8 | +5.4 | #78 of 297, top 27% |

## Closest competitors

The models ranked just above and below GPT-5.6 Luna. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to GPT-5.6 Luna
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [GLM-5.3](https://noometry.com/models/glm-5-3) | #26 | 54.8 | $2.15 | — | [Compare](https://noometry.com/compare/glm-5-3-vs-gpt-5-6-luna) |
| [Muse Spark 1.3](https://noometry.com/models/muse-spark-1-3) | #27 | 54.8 | $2 | — | [Compare](https://noometry.com/compare/gpt-5-6-luna-vs-muse-spark-1-3) |
| [Gemini 3 Pro](https://noometry.com/models/gemini-3-pro) | #28 | 54.8 | — | 1 | [Compare](https://noometry.com/compare/gemini-3-pro-vs-gpt-5-6-luna) |
| [Claude Sonnet 5](https://noometry.com/models/claude-sonnet-5) | #29 | 54.6 | $4 | — | [Compare](https://noometry.com/compare/claude-sonnet-5-vs-gpt-5-6-luna) |
| [DeepSeek V4 Pro](https://noometry.com/models/deepseek-v4-pro) | #31 | 54.3 | $0.99 | 16 | [Compare](https://noometry.com/compare/deepseek-v4-pro-vs-gpt-5-6-luna) |
| [Gemini 3.5 Flash](https://noometry.com/models/gemini-3-5-flash) | #32 | 54.2 | $3.38 | — | [Compare](https://noometry.com/compare/gemini-3-5-flash-vs-gpt-5-6-luna) |
| [Gemini 3.6 Flash](https://noometry.com/models/gemini-3-6-flash) | #33 | 54.1 | $1.50 | — | [Compare](https://noometry.com/compare/gemini-3-6-flash-vs-gpt-5-6-luna) |
| [GPT-5.2](https://noometry.com/models/gpt-5-2) | #34 | 54.1 | $4.81 | 15 | [Compare](https://noometry.com/compare/gpt-5-2-vs-gpt-5-6-luna) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Coding

GPT-5.6 Luna Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [DeepSWE](https://noometry.com/benchmarks/deepswe) | 44.2% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [DeepSWE](https://noometry.com/benchmarks/deepswe) | 1.5% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [DeepSWE](https://noometry.com/benchmarks/deepswe) | 67.2% | #12 of 29, top 42% | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [DeepSWE](https://noometry.com/benchmarks/deepswe) | 11.3% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [DeepSWE](https://noometry.com/benchmarks/deepswe) | 56.9% |  | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [FrontierCode](https://noometry.com/benchmarks/frontiercode) | 39.8% | #22 of 37, top 60% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CursorBench](https://noometry.com/benchmarks/cursorbench) | 29.4% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CursorBench](https://noometry.com/benchmarks/cursorbench) | 16% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CursorBench](https://noometry.com/benchmarks/cursorbench) | 35.9% | #13 of 14, top 93% | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CursorBench](https://noometry.com/benchmarks/cursorbench) | 22.2% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CursorBench](https://noometry.com/benchmarks/cursorbench) | 33% |  | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena WebDev](https://noometry.com/benchmarks/arena-webdev) | 1519 | #42 of 113, top 38% |  | [LMArena](https://lmarena.ai/leaderboard/webdev) | 2026-10-08 |
| [SciCode](https://noometry.com/benchmarks/scicode) | 50.7% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SciCode](https://noometry.com/benchmarks/scicode) | 45.6% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SciCode](https://noometry.com/benchmarks/scicode) | 53.6% | #30 of 121, top 25% | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SciCode](https://noometry.com/benchmarks/scicode) | 45.8% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SciCode](https://noometry.com/benchmarks/scicode) | 39.9% |  | none | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SciCode](https://noometry.com/benchmarks/scicode) | 50% |  | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 60.9% | #28 of 119, top 24% | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1466 | #64 of 294, top 22% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [ALE-Bench](https://noometry.com/benchmarks/ale-bench) | 1,667 | #11 of 105, top 11% | max | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Agentic & Tool Use

GPT-5.6 Luna Agentic & Tool Use benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [APEX-Agents](https://noometry.com/benchmarks/apex-agents) | 43% | #35 of 49, top 72% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [BALROG](https://noometry.com/benchmarks/balrog) | 45.6% | #8 of 35, top 23% | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [GDP.pdf](https://noometry.com/benchmarks/gdp-pdf) | 22.7% | #18 of 36, top 50% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [GDP.pdf](https://noometry.com/benchmarks/gdp-pdf) | 22.7% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Vending-Bench 2](https://noometry.com/benchmarks/vending-bench-2) | 4,095 | #35 of 60, top 59% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Reasoning

GPT-5.6 Luna Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 29.3% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 5.1% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 59.5% | #30 of 83, top 37% | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 7.4% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-2](https://noometry.com/benchmarks/arc-agi-2) | 47.6% |  | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SimpleBench](https://noometry.com/benchmarks/simplebench) | 46.8% | #44 of 77, top 58% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SimpleBench](https://noometry.com/benchmarks/simplebench) | 46.8% |  | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Kagi LLM Benchmark](https://noometry.com/benchmarks/kagi-reasoning) | 49.1% | #66 of 99, top 67% |  | [Kagi LLM Benchmark](https://help.kagi.com/kagi/ai/llm-benchmark.html) |  |
| [NYT Connections (extended)](https://noometry.com/benchmarks/nyt-connections) | 69.4% | #50 of 91, top 55% | high reasoning | [Lech Mazur benchmarks](https://github.com/lechmazur/nyt-connections) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 76.5% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 34.2% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 88% | #29 of 83, top 35% | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 56.5% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [ARC-AGI-1](https://noometry.com/benchmarks/arc-agi-1) | 87.7% |  | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 16.6% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 2.6% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 20.6% | #23 of 134, top 18% | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 4.9% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 0.3% |  | none | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [CritPt](https://noometry.com/benchmarks/critpt) | 20.6% |  | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 21% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-07 |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 40% | #20 of 129, top 16% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-09 |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 2% |  | none | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-07 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1451 | #60 of 297, top 21% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 17% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 21% | #40 of 74, top 55% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-28 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 12% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 20% |  | none | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-30 |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 86.7% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 80% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 88.8% |  | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 83.2% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 69.3% |  | none | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 89.1% | #45 of 151, top 30% | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 47.4% |  | high | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 43.8% |  | low | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 48.5% | #24 of 125, top 20% | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 44.3% |  | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 41.4% |  | none | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 48.5% |  | xhigh | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Surface Evolver Bench](https://noometry.com/benchmarks/surface-evolver-bench) | 61.9% | #9 of 25, top 36% | medium | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 156.39 | #23 of 213, top 11% |  | [Epoch AI](https://epoch.ai/eci) | 2026-07-09 |

### Math

GPT-5.6 Luna Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [FrontierMath (Tiers 1-3)](https://noometry.com/benchmarks/frontiermath) | 41.4% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-29 |
| [FrontierMath (Tiers 1-3)](https://noometry.com/benchmarks/frontiermath) | 82.1% | #14 of 81, top 18% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-09 |
| [FrontierMath (Tiers 1-3)](https://noometry.com/benchmarks/frontiermath) | 39.6% |  | none | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-29 |
| [FrontierMath Tier 4](https://noometry.com/benchmarks/frontiermath-tier-4) | 61% | #14 of 63, top 23% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-09 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 66.7% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-07 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 98.3% | #22 of 173, top 13% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-09 |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 40% |  | none | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-07 |
| [ProofBench](https://noometry.com/benchmarks/proofbench) | 60% | #19 of 77, top 25% | max | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1458 | #54 of 285, top 19% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Knowledge

GPT-5.6 Luna Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 82.3% |  | low | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-07 |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 91.6% | #25 of 186, top 14% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-07-09 |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 63.6% |  | none | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-07 |
| [SimpleQA Verified](https://noometry.com/benchmarks/simpleqa-verified) | 41% | #42 of 77, top 55% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-10 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1478 | #42 of 273, top 16% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multimodal

GPT-5.6 Luna Multimodal benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Vision](https://noometry.com/benchmarks/arena-vision) | 1258 | #50 of 122, top 41% | xhigh | [LMArena](https://lmarena.ai/leaderboard/vision) | 2026-10-09 |
| [Blueprint-Bench 2](https://noometry.com/benchmarks/blueprint-bench-2) | 22.6% | #23 of 31, top 75% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Furniture Assembly](https://noometry.com/benchmarks/furniture-assembly) | 42.5% | #14 of 31, top 46% | max | [Epoch AI](https://epoch.ai/benchmarks) | 2026-09-10 |
| [LMArena Document](https://noometry.com/benchmarks/arena-document) | 1457 | #18 of 38, top 48% | xhigh | [LMArena](https://lmarena.ai/leaderboard/document) | 2026-09-13 |

### Multilingual

GPT-5.6 Luna Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1417 | #78 of 297, top 27% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1470 | #73 of 285, top 26% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1456 | #58 of 223, top 27% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1454 | #41 of 231, top 18% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1411 | #50 of 211, top 24% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1415 | #40 of 213, top 19% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1428 | #72 of 283, top 26% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1448 | #55 of 226, top 25% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

GPT-5.6 Luna Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1437 | #53 of 298, top 18% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

GPT-5.6 Luna Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1436 | #71 of 291, top 25% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

GPT-5.6 Luna Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1431 | #77 of 297, top 26% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1396 | #86 of 295, top 30% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [EQ-Bench Creative Writing](https://noometry.com/benchmarks/eqbench-creative-writing) | 1829 | #21 of 115, top 19% |  | [EQ-Bench](https://eqbench.com/creative_writing.html) |  |
| [EQ-Bench 4](https://noometry.com/benchmarks/eqbench-4) | 1156 | #19 of 28, top 68% |  | [EQ-Bench](https://eqbench.com/) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1434 | #78 of 295, top 27% | xhigh | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## API pricing by provider

GPT-5.6 Luna API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [azure](https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models) | $0.20 | $1.20 | $0.02 | 2026-10-10 |
| [bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) | $0.20 | $1.20 | $0.02 | 2026-10-10 |
| [openai](https://platform.openai.com/docs/models) | $0.20 | $1.20 | $0.02 | 2026-10-10 |
| [openrouter](https://openrouter.ai/openai/gpt-5.6-luna) | $0.20 | $1.20 | $0.02 | 2026-10-10 |

[All OpenAI API prices →](https://noometry.com/llm-pricing/openai) [Estimate your cost →](https://noometry.com/tools/cost-calculator)

## Compare GPT-5.6 Luna

-   [GPT-5.6 Luna vs Claude Sonnet 5](https://noometry.com/compare/claude-sonnet-5-vs-gpt-5-6-luna)
-   [GPT-5.6 Luna vs DeepSeek V4 Pro](https://noometry.com/compare/deepseek-v4-pro-vs-gpt-5-6-luna)
-   [GPT-5.6 Luna vs Gemini 3 Pro](https://noometry.com/compare/gemini-3-pro-vs-gpt-5-6-luna)
-   [GPT-5.6 Luna vs Gemini 3.5 Flash](https://noometry.com/compare/gemini-3-5-flash-vs-gpt-5-6-luna)
-   [GPT-5.6 Luna vs Muse Spark 1.3](https://noometry.com/compare/gpt-5-6-luna-vs-muse-spark-1-3)
-   [GPT-5.6 Luna vs Gemini 3.6 Flash](https://noometry.com/compare/gemini-3-6-flash-vs-gpt-5-6-luna)
-   [GPT-5.6 Luna vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-gpt-5-6-luna)
-   [GPT-5.6 Luna vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-gpt-5-6-luna)
-   [GPT-5.6 Luna vs Kimi K3](https://noometry.com/compare/gpt-5-6-luna-vs-kimi-k3)
-   [GPT-5.6 Luna vs Grok 4.6](https://noometry.com/compare/gpt-5-6-luna-vs-grok-4-6)
-   [GPT-5.6 Luna vs Qwen3.8 Max](https://noometry.com/compare/gpt-5-6-luna-vs-qwen3-8-max)
-   [GPT-5.6 Luna vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-gpt-5-6-luna)
-   [GPT-5.6 Luna vs MiMo-V2.6-Pro](https://noometry.com/compare/gpt-5-6-luna-vs-mimo-v2-6-pro)

## Other OpenAI models

-   [GPT-6 Astra](https://noometry.com/models/gpt-6-astra)70.8
-   [GPT-6.1 Sol](https://noometry.com/models/gpt-6-1-sol)65.6
-   [GPT-5.6 Sol](https://noometry.com/models/gpt-5-6-sol)65.0
-   [GPT-5.5 Pro](https://noometry.com/models/gpt-5-5-pro)64.3
-   [GPT-5.5](https://noometry.com/models/gpt-5-5)63.4
-   [GPT-6 Sol](https://noometry.com/models/gpt-6-sol)61.8
-   [GPT-5.4](https://noometry.com/models/gpt-5-4)59.4
-   [GPT-5.6 Terra](https://noometry.com/models/gpt-5-6-terra)59.2

## Frequently asked questions

### How good is GPT-5.6 Luna?

GPT-5.6 Luna by OpenAI ranks 30th of 354 ranked models on the Noometry Index as of October 2026, with a score of 54.6. Its strongest category is math, where it ranks 14th. API pricing starts at $0.20 per million input tokens and $1.20 per million output tokens, with a 1.05M-token context window.

### How much does GPT-5.6 Luna cost?

GPT-5.6 Luna costs $0.20 per million input tokens and $1.20 per million output tokens on OpenAI's own API, with cached input at $0.02.

### What is GPT-5.6 Luna's context window?

GPT-5.6 Luna accepts up to 1.05M tokens of input and can write up to 128K tokens in one response.

### Is GPT-5.6 Luna open source?

No. GPT-5.6 Luna is proprietary and available only through OpenAI's API and partner platforms.

### How fast is GPT-5.6 Luna?

GPT-5.6 Luna generated about 12 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.

### What are GPT-5.6 Luna's strengths and weaknesses?

Relative to other ranked models, GPT-5.6 Luna places best in math, coding, writing & preference and lowest in agentic & tool use, long context, multilingual.

### What is GPT-5.6 Luna best at?

Its best category is math, where it ranks 14th on Noometry.

### Cite this page

Noometry. (2026). GPT-5.6 Luna benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/gpt-5-6-luna

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/gpt-5-6-luna.md).