Skip to main content
Radar

Provider changes are easy to miss. Radar watches releases, pricing, deprecations, and incidents at the source.Provider changes are easy to miss.

See Radar

Model profile · OpenAI

GPT-5.6 Luna

CurrentReleased Jul 9, 2026ProprietaryReasoning1.05M context

Released Jul 9, 2026 see all recent releases

GPT-5.6 Luna scores 66.8 out of 100 and ranks #26 of 218. This profile shows 23 source-displayable benchmark rows; its strongest eligible category is Coding at #6. API pricing is $0.2 input and $1.2 output per million tokens, with cached input at $0.02.

Data as of August 11, 2026 · How the score is built

Strongest published evidence

Coding ranks #6. Particularly well-suited for software development and code generation tasks.

Validate before choosing

23 published rows leave some tracked benchmark slots empty. Independent runtime speed has not been measured.

Decision snapshot

Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.

Capability

66.8/100

field median 57.7

#26 of 218 ranked models

Price

$0.20input / $1.20 output

input median $1

cached $0.020 · blended $0.70

Speed

Not measured

field median 93 tok/s

Time to first token not measured

Context

1.05Mtokens

field median 201,500

Maximum output length is tracked separately

Capability shape

Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.

GPT-5.6 Luna category percentile values

  • Agentic73rd percentile
  • Coding96th percentile
  • ReasoningNot eligible
  • Knowledge80th percentile
  • MathNot eligible
  • MultilingualNot eligible
  • Multimodal41st percentile
  • Instruction followingNot eligible

The dashed outline is median of 6 nearest peers.

Eligible category ranks

  1. Agentic#35/129
  2. Coding#6/135
  3. ReasoningNot ranked
  4. Knowledge#12/56
  5. MathNot ranked
  6. MultilingualNot ranked
  7. Multimodal#21/35
  8. Inst. FollowingNot ranked
Top decileTop quartileMid-fieldNot eligible

What it costs to get this score

Published API price against the public score. The x-axis uses a log scale; the dashed path marks models that are not beaten by a cheaper, higher-scoring option. Price uses average of published input and output rates.

Explore all models

The chart opens on the current model. Scroll horizontally to inspect the full price axis.

Current modelGPT-5.6 Luna · 66.8 score · $0.70 blended per million tokens
405060708090$0.50$1$5$10$25↘ frontierGPT-5.6 Luna

Horizontal: blended price per million tokens, log scale · Vertical: public score

How much of this is verified

Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.

  1. Agentic6/6 verified
  2. Coding5/5 verified
  3. Reasoning2/2 verified
  4. Knowledge4/4 verified
  5. Math3/3 verified
  6. MultilingualNot measured
  7. Multimodal2/2 verified
  8. Inst. FollowingNot measured
Verified sourceProvisionalNot measured

Spec sheet

Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.

API model ID
gpt-5.6-lunaOpenAI model catalog
Context window
1.05MOpenAI model catalog
Maximum output
Not sourced yet
Knowledge cutoff
Not sourced yet
Input modalities
text, imageOpenAI model catalog
Output modalities
textOpenAI model catalog
Parameters
Not disclosed by the provider
Availability
OpenAI Responses APIOpenAI model catalog
Cloud regions
Not tracked yet
Lifecycle
activeOpenAI model catalog
API capabilities
Tool calling, structured outputs, and batch support are not tracked yet
Prompt caching
Published at $0.020 per million cached input tokensOpenAI pricing
Self-host
Weights are not published
Rate limits
Not tracked yet

Category score record

Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #35 of 129Percentile 73rdWeight 22%6 benchmarksVerified54.6
CodingRank #6 of 135Percentile 96thWeight 20%5 benchmarksVerified72.6
ReasoningRank Not rankedWeight 17%2 benchmarksVerified65.6
KnowledgeRank #12 of 56Percentile 80thWeight 12%4 benchmarksVerified81.2
MathRank Not rankedWeight 5%3 benchmarksVerified96.9
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalRank #21 of 35Percentile 41stWeight 12%2 benchmarksVerified66.0
Inst. FollowingWeight 5%0 benchmarksNot measuredNot measured

Benchmark ledger

Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.

Coding5 rows
Coding benchmark values, best verified comparison, weight, and source status
SWE-bench ProScore62.7%Versus best verified row

Best verified: Claude Mythos 5 · 80.3%

Gap17.6 behindWeightWeighted 10%
Provider exact
Terminal-Bench 2.0Score84.7%Versus best verified row

Best verified: GPT-5.6 Sol · 91.9%

Gap7.2 behindWeightDisplay only
Provider exact
deepSweScore67.2%Versus best verified row

Best verified: GPT-5.6 Sol · 72.7%

Gap5.5 behindWeightDisplay only
Provider exact
FrontierCode 1.1 ExtendedScore55.1%Versus best verified row

Best verified: Claude Opus 5 · 63.6%

Gap8.5 behindWeightDisplay only
cursorBench32Score61.1%Versus best verified row

Best verified: Claude Fable 5 · 70.5%

Gap9.4 behindWeightDisplay only
Agentic6 rows
Agentic benchmark values, best verified comparison, weight, and source status
Terminal-Bench 2.0Score84.7%Versus best verified row

Best verified: GPT-5.6 Sol · 91.9%

Gap7.2 behindWeightWeighted 38%
Provider exact
BrowseCompScore83.3%Versus best verified row

Best verified: GPT-5.6 Sol · 92.2%

Gap8.9 behindWeightWeighted 28%
Provider exact
OSWorld 2.0Score45.6%Versus best verified row

Best verified: Claude Opus 5 · 70.6%

Gap25 behindWeightDisplay only
Provider exact
CyberGymScore77.9%Versus best verified row

Best verified: Fugu Cyber · 86.9%

Gap9 behindWeightDisplay only
Provider exact
ExploitGymScore12.4%Versus best verified row

Best verified: GPT-5.6 Sol · 33.7%

Gap21.3 behindWeightDisplay only
Provider exact
ToolathlonScore53.4%Versus best verified row

Best verified: Muse Spark 1.1 · 75.6%

Gap22.2 behindWeightDisplay only
Provider exact
Reasoning2 rows
Reasoning benchmark values, best verified comparison, weight, and source status
ARC-AGI-2Abstraction and Reasoning Corpus for AGI v2Score59.5%Versus best verified row

Best verified: GPT-5.6 Sol · 92.5%

Gap33 behindWeightWeighted 31%
ARC-AGI-3Abstraction and Reasoning Corpus for AGI v3Score0.2%Versus best verified row

Best verified: Claude Opus 5 · 30.2%

Gap30 behindWeightDisplay only
Knowledge4 rows
Knowledge benchmark values, best verified comparison, weight, and source status
GPQAGraduate-Level Google-Proof Q&AScore92.3%Versus best verified row

Best verified: Sakana Fugu-Ultra · 95.5%

Gap3.2 behindWeightWeighted 7%
Provider exact
GPQA-DGPQA DiamondScore92.3%Versus best verified row

Best verified: Sakana Fugu-Ultra · 95.5%

Gap3.2 behindWeightDisplay only
Provider exact
HealthBench ProfessionalScore55.7%Versus best verified row

Best verified: GPT-5.6 Sol · 60.5%

Gap4.8 behindWeightDisplay only
Provider exact
HealthBench HardScore32.0%Versus best verified row

Best verified: Muse Spark · 42.8%

Gap10.8 behindWeightDisplay only
Math3 rows
Math benchmark values, best verified comparison, weight, and source status
FrontierMath v2 (Tiers 1-3)FrontierMath v2 Tiers 1-3Score78.600%Versus best verified row

Best verified: GPT-5.6 Sol · 89.000%

Gap10.4 behindWeightWeighted 30%
Provider exact
FrontierMath v2 (Tier 4)FrontierMath v2 Tier 4Score58.500%Versus best verified row

Best verified: GPT-5.6 Sol · 83.000%

Gap24.5 behindWeightWeighted 10%
Provider exact
FrontierMath (legacy)FrontierMath legacy aggregateScore78.6%Versus best verified row

Best verified: GPT-5.6 Sol · 89%

Gap10.4 behindWeightDisplay only
Provider exact
Multimodal2 rows
Multimodal benchmark values, best verified comparison, weight, and source status
MMMU-ProMassive Multi-discipline Multimodal Understanding ProScore78.4%Versus best verified row

Best verified: GPT-5.4 Pro · 94%

Gap15.6 behindWeightWeighted 45%
Provider exact
MMMU-Pro w/ PythonMMMU-Pro with PythonScore79.5%Versus best verified row

Best verified: GPT-5.6 Sol · 84.6%

Gap5.1 behindWeightDisplay only
Provider exact
External signals1 row
External signals benchmark values, best verified comparison, weight, and source status
ExploitBenchExploitBench v8-benchScore33%Versus best verified row

Best verified: GPT-5.6 Sol · 74%

Gap40.3 behindWeightDisplay only
Provider exact

Lineage

The sequence follows explicit supersedes links. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.

Jul 9, 2026 · you are here

GPT-5.6 Luna

Score 66.8 · $0.2 / $1.2

luna · luna

How to read this profile

The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.

GPT-5.6 Luna ranks #26 of 218 on the public leaderboard with a score of 66.77/100. It does not yet have enough sourced coverage for a verified position.

GPT-5.6 Luna is a proprietary model with a 1.05M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.

GPT-5.6 Luna sits in the GPT-5.6 family with GPT-5.6 Sol, GPT-5.6 Terra. 23 of 381 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.

Its strongest eligible category is Coding at #6, while its lowest eligible position is Agentic at #35. particularly well-suited for software development and code generation tasks.

Radar

GPT-5.6 Luna release history

Full release history

Frequently asked questions

How does GPT-5.6 Luna perform overall in AI benchmarks?

GPT-5.6 Luna ranks #26 out of 218 models on the public BenchAlign leaderboard, with a score of 66.77/100. Its evidence status is Estimated, and this profile shows 23 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.

Is GPT-5.6 Luna good for knowledge and understanding?

GPT-5.6 Luna ranks #12 out of 56 eligible models for knowledge and understanding, with a public category score of 81.2/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is GPT-5.6 Luna good for coding and programming?

GPT-5.6 Luna ranks #6 out of 135 eligible models for coding and programming, with a public category score of 72.6/100. That places it in the current top ten for this category. Check the underlying rows before treating the aggregate as a workload guarantee.

Is GPT-5.6 Luna good for mathematics?

GPT-5.6 Luna has source-displayable benchmark coverage for mathematics, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is GPT-5.6 Luna good for reasoning and logic?

GPT-5.6 Luna has source-displayable benchmark coverage for reasoning and logic, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is GPT-5.6 Luna good for agentic tool use and computer tasks?

GPT-5.6 Luna ranks #35 out of 129 eligible models for agentic tool use and computer tasks, with a public category score of 54.6/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is GPT-5.6 Luna good for multimodal and grounded tasks?

GPT-5.6 Luna ranks #21 out of 35 eligible models for multimodal and grounded tasks, with a public category score of 66/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Which sibling models are related to GPT-5.6 Luna?

GPT-5.6 Luna belongs to the GPT-5.6 family. Related tracked variants include GPT-5.6 Sol, GPT-5.6 Terra. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.

Does GPT-5.6 Luna have full benchmark coverage on BenchLM?

No. GPT-5.6 Luna currently has 43 source-displayable rows across 381 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.

What is the context window size of GPT-5.6 Luna?

GPT-5.6 Luna has a documented context window of 1.05M. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.

Last updated August 11, 2026. Runtime fields remain blank until a sourced snapshot exists.

Watch GPT-5.6 Luna in the weekly brief

Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.

Read a sample issue

Join 2,000+ readers.