Noometry

OpenAI, proprietary

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.

Last verified

Noometry rank
#30 of 354
Index score
54.6
Evidence
Confirmed 52 results
Provider
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
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.

  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
CategoryScoreRankResults
Coding54.5#287
Agentic & Tool Use34.4#453
Reasoning47.6#4312
Math77.7#145
Knowledge58.5#343
Multimodal42.7#283
Multilingual52.8#781
Instruction Following75.6#571
Long Context43.9#821
Writing & Preference68.0#295

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

CategoryScorevs medianRank
Math77.7+41.1#14 of 327, top 5%
Coding54.5+15.8#28 of 340, top 9%
Writing & Preference68.0+14.2#29 of 312, top 10%

Weakest categories

CategoryScorevs medianRank
Agentic & Tool Use34.4+4.1#45 of 154, top 30%
Long Context43.9+3.0#82 of 296, top 28%
Multilingual52.8+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.

ModelRankScoreBlended $/MSpeed
GLM-5.3#2654.8$2.15—Compare
Muse Spark 1.3#2754.8$2—Compare
Gemini 3 Pro#2854.8—1Compare
Claude Sonnet 5#2954.6$4—Compare
DeepSeek V4 Pro#3154.3$0.9916Compare
Gemini 3.5 Flash#3254.2$3.38—Compare
Gemini 3.6 Flash#3354.1$1.50—Compare
GPT-5.2#3454.1$4.8115Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

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

BenchmarkScorePositionSettingSourceDate
DeepSWE44.2%highEpoch AI
DeepSWE1.5%lowEpoch AI
DeepSWE67.2%#12 of 29, top 42%maxEpoch AI
DeepSWE11.3%mediumEpoch AI
DeepSWE56.9%xhighEpoch AI
FrontierCode39.8%#22 of 37, top 60%Epoch AI
CursorBench29.4%highEpoch AI
CursorBench16%lowEpoch AI
CursorBench35.9%#13 of 14, top 93%maxEpoch AI
CursorBench22.2%mediumEpoch AI
CursorBench33%xhighEpoch AI
LMArena WebDev1519#42 of 113, top 38%LMArena2026-10-08
SciCode50.7%highEpoch AI
SciCode45.6%lowEpoch AI
SciCode53.6%#30 of 121, top 25%maxEpoch AI
SciCode45.8%mediumEpoch AI
SciCode39.9%noneEpoch AI
SciCode50%xhighEpoch AI
WeirdML60.9%#28 of 119, top 24%highEpoch AI
LMArena Coding1466#64 of 294, top 22%xhighLMArena2026-10-08
ALE-Bench1,667#11 of 105, top 11%maxEpoch AI

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
APEX-Agents43%#35 of 49, top 72%Epoch AI
BALROG45.6%#8 of 35, top 23%maxEpoch AI
GDP.pdf22.7%#18 of 36, top 50%Epoch AI
GDP.pdf22.7%mediumEpoch AI
Vending-Bench 24,095#35 of 60, top 59%Epoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
ARC-AGI-229.3%highEpoch AI
ARC-AGI-25.1%lowEpoch AI
ARC-AGI-259.5%#30 of 83, top 37%maxEpoch AI
ARC-AGI-27.4%mediumEpoch AI
ARC-AGI-247.6%xhighEpoch AI
SimpleBench46.8%#44 of 77, top 58%Epoch AI
SimpleBench46.8%xhighEpoch AI
Kagi LLM Benchmark49.1%#66 of 99, top 67%Kagi LLM Benchmark
NYT Connections (extended)69.4%#50 of 91, top 55%high reasoningLech Mazur benchmarks
ARC-AGI-176.5%highEpoch AI
ARC-AGI-134.2%lowEpoch AI
ARC-AGI-188%#29 of 83, top 35%maxEpoch AI
ARC-AGI-156.5%mediumEpoch AI
ARC-AGI-187.7%xhighEpoch AI
CritPt16.6%highEpoch AI
CritPt2.6%lowEpoch AI
CritPt20.6%#23 of 134, top 18%maxEpoch AI
CritPt4.9%mediumEpoch AI
CritPt0.3%noneEpoch AI
CritPt20.6%xhighEpoch AI
Chess Puzzles21%lowEpoch AI2026-08-07
Chess Puzzles40%#20 of 129, top 16%maxEpoch AI2026-07-09
Chess Puzzles2%noneEpoch AI2026-08-07
LMArena Hard Prompts1451#60 of 297, top 21%xhighLMArena2026-10-08
Mystery Game Puzzles17%lowEpoch AI2026-08-27
Mystery Game Puzzles21%#40 of 74, top 55%maxEpoch AI2026-07-28
Mystery Game Puzzles12%mediumEpoch AI2026-08-27
Mystery Game Puzzles20%noneEpoch AI2026-08-30
DTBench86.7%highEpoch AI
DTBench80%lowEpoch AI
DTBench88.8%maxEpoch AI
DTBench83.2%mediumEpoch AI
DTBench69.3%noneEpoch AI
DTBench89.1%#45 of 151, top 30%xhighEpoch AI
LMCA47.4%highEpoch AI
LMCA43.8%lowEpoch AI
LMCA48.5%#24 of 125, top 20%maxEpoch AI
LMCA44.3%mediumEpoch AI
LMCA41.4%noneEpoch AI
LMCA48.5%xhighEpoch AI
Surface Evolver Bench61.9%#9 of 25, top 36%mediumEpoch AI
Epoch Capabilities Index156.39#23 of 213, top 11%Epoch AI2026-07-09

Math

BenchmarkScorePositionSettingSourceDate
FrontierMath (Tiers 1-3)41.4%lowEpoch AI2026-08-29
FrontierMath (Tiers 1-3)82.1%#14 of 81, top 18%maxEpoch AI2026-07-09
FrontierMath (Tiers 1-3)39.6%noneEpoch AI2026-08-29
FrontierMath Tier 461%#14 of 63, top 23%maxEpoch AI2026-07-09
OTIS Mock AIME 2024-202566.7%lowEpoch AI2026-08-07
OTIS Mock AIME 2024-202598.3%#22 of 173, top 13%maxEpoch AI2026-07-09
OTIS Mock AIME 2024-202540%noneEpoch AI2026-08-07
ProofBench60%#19 of 77, top 25%maxEpoch AI
LMArena Math1458#54 of 285, top 19%xhighLMArena2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond82.3%lowEpoch AI2026-08-07
GPQA Diamond91.6%#25 of 186, top 14%maxEpoch AI2026-07-09
GPQA Diamond63.6%noneEpoch AI2026-08-07
SimpleQA Verified41%#42 of 77, top 55%maxEpoch AI2026-08-10
LMArena Expert1478#42 of 273, top 16%xhighLMArena2026-10-08

Multimodal

BenchmarkScorePositionSettingSourceDate
LMArena Vision1258#50 of 122, top 41%xhighLMArena2026-10-09
Blueprint-Bench 222.6%#23 of 31, top 75%Epoch AI
Furniture Assembly42.5%#14 of 31, top 46%maxEpoch AI2026-09-10
LMArena Document1457#18 of 38, top 48%xhighLMArena2026-09-13

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1417#78 of 297, top 27%xhighLMArena2026-10-08
LMArena Chinese1470#73 of 285, top 26%xhighLMArena2026-10-08
LMArena French1456#58 of 223, top 27%xhighLMArena2026-10-08
LMArena German1454#41 of 231, top 18%xhighLMArena2026-10-08
LMArena Japanese1411#50 of 211, top 24%xhighLMArena2026-10-08
LMArena Korean1415#40 of 213, top 19%xhighLMArena2026-10-08
LMArena Russian1428#72 of 283, top 26%xhighLMArena2026-10-08
LMArena Spanish1448#55 of 226, top 25%xhighLMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1437#53 of 298, top 18%xhighLMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1436#71 of 291, top 25%xhighLMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1431#77 of 297, top 26%xhighLMArena2026-10-08
LMArena Creative Writing1396#86 of 295, top 30%xhighLMArena2026-10-08
EQ-Bench Creative Writing1829#21 of 115, top 19%EQ-Bench
EQ-Bench 41156#19 of 28, top 68%EQ-Bench
LMArena Multi-Turn1434#78 of 295, top 27%xhighLMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
azure$0.20$1.20$0.022026-10-10
bedrock$0.20$1.20$0.022026-10-10
openai$0.20$1.20$0.022026-10-10
openrouter$0.20$1.20$0.022026-10-10

All OpenAI API prices → Estimate your cost →

Compare GPT-5.6 Luna

Other OpenAI models

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.