Skip to main content
BenchLM
Data

GPT-5.6 Luna vs o1

Updated November 10, 2026. Rank says GPT-5.6 Luna is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

GPT-5.6 Luna has the higher public point estimate, 63.72 versus 38.52. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. 2 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
OpenAI logo
GPT-5.6 Luna

OpenAI

63.72/100

Supported · Public rank #38

90% interval 58.2–69.3

Model B
OpenAI logo
o1

OpenAI

38.52/100

Estimated · Public rank #147

Conditional range 24.2–52.9

API price per 1M tokens

GPT-5.6 Luna: $0.20 input / $1.20 output

o1: $15 input / $60 output

Context window

GPT-5.6 Luna: 1.05M

o1: 200K

Released

GPT-5.6 Luna: July 9, 2026

o1: December 1, 2024

Shared results
2
GPT-5.6 Luna only
33
o1 only
2
Like-for-like categories
1 / 8
Supported: GPT-5.6 Luna · Estimated: o1. Conditional ranges do not establish rank confidence.How the comparison works

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

  • Long documents

    Prompts that approach the documented context limit

    GPT-5.6 Luna

    GPT-5.6 Luna has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    GPT-5.6 Luna

    GPT-5.6 Luna has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates
Show secondary and unsupported calls

  • Repository review cost

    50K fresh input + 3K output tokens

    GPT-5.6 Luna

    GPT-5.6 Luna has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    O1 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.

    Confidence: limited

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    O1 is not ranked on the public lane for agentic, so no winner is named for agentic.

    Confidence: limited

  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    Not enough matched evidence

    The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. o1 does not fit this workload in one request. o1 has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

61.9GPT-5.6 Luna30.7o1

Directional only · BenchAlign v5.8

GPT-5.6 Luna has the higher coding point estimate. Conditional score ranges do not establish rank confidence.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Open the coding leaderboardShortlist models for this job
Same basis rules as the category table below

Or describe your own job

The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, reasoning, multimodal, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Knowledge

Like-for-like
GPT-5.6 Luna
63.1
Supported · #40/179
o1
40.7
Supported · #113/179
Basis
BenchAlign v5.8 lane · 6 vs 2 public rows
Reading
GPT-5.6 Luna leads

Coding

Directional only
GPT-5.6 Luna
61.9
Supported · #17/158
o1
30.7
Estimated · #105/158
Basis
BenchAlign v5.8 lane · 8 vs 0 public rows
Reading
Directional only

Reasoning

Directional only
GPT-5.6 Luna
58.3
Supported · #36/158
o1
33.2
Estimated · #107/158
Basis
BenchAlign v5.8 lane · 3 vs 0 public rows
Reading
Directional only

Agentic

Not comparable
GPT-5.6 Luna
59.1
Supported · #33/132
o1
Not ranked
Basis
BenchAlign v5.8 lane · 11 vs 0 public rows
Reading
Not comparable

Multimodal

Not comparable
GPT-5.6 Luna
65.4
Supported · #23/67
o1
Not ranked
Basis
BenchAlign v5.8 lane · 4 vs 0 public rows
Reading
Not comparable

Multilingual

Not comparable
GPT-5.6 Luna
Not ranked
o1
Not ranked
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Instruction following

Not comparable
GPT-5.6 Luna
Not ranked
o1
86.0
#49/157
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
GPT-5.6 Luna
78.9
Unranked · 3 rankable rows
o1
29.8
Unranked · 1 rankable row
Basis
Provisional lane · 2 vs 1 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, reasoning, multimodal, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

GPT-5.6 Luna
$0.0008
Fits in one request
o1
$0.045
Fits in one request

GPT-5.6 Luna has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

GPT-5.6 Luna
$0.0136
Fits in one request
o1
$0.93
Fits in one request

GPT-5.6 Luna has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

GPT-5.6 Luna
$0.02
Fits in one request
o1
$3.90
Does not fit in one request
Cached input priced at the published list-input rate

o1 does not fit this workload in one request. o1 has no published cached-input rate, so cached tokens use its listed input rate.

Your workload

Enter a month of tokens to price it at both models’ listed API rates.

GPT-5.6 Luna
$4.40
per month
o1
$270.00
per month

Standard listed rates, no batch or volume discounts.

Cached input falls back to the list input rate only where a cached rate is unpublished

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Context window

Maximum documented context; output-token limits may be lower.

GPT-5.6 Luna

1.05M

OpenAI model catalog

o1

200K

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

GPT-5.6 Luna

$0.02 per 1M cached input tokens

OpenAI pricing

o1

Not published

Provider availability

GPT-5.6 Luna

Generally Available · OpenAI Responses API

OpenAI model catalog

o1

Not sourced

Reasoning profile

GPT-5.6 Luna

Reasoning

o1

Reasoning

Weight access

GPT-5.6 Luna

Proprietary

o1

Proprietary

License

GPT-5.6 Luna

Proprietary

o1

Proprietary

Release date

GPT-5.6 Luna

2026-07-09

o1

2024-12-01

If you already use one of these models

Deployment change
Both entries list OpenAI as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
Quality signal
GPT-5.6 Luna has the higher public point estimate, 63.72 versus 38.52. Their conditional score ranges do not overlap. These ranges do not establish rank confidence.
Workload cost
Repository review: $0.0136 vs $0.93. Cache-heavy agent loop: $0.02 vs $3.90.
Context tradeoff
GPT-5.6 Luna has the larger documented window (1.05M).
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, GPT-5.6 Luna or o1?

GPT-5.6 Luna has the higher public point estimate, 63.72 versus 38.52. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.

Which is better for coding, GPT-5.6 Luna or o1?

GPT-5.6 Luna scores higher for coding on the public lane, 61.9 to 30.7. O1 is scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.

Which is better for agentic tasks, GPT-5.6 Luna or o1?

O1 is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, GPT-5.6 Luna or o1?

For the stated presets, chat costs $0.0008 on GPT-5.6 Luna and $0.045 on o1; repository review costs $0.0136 and $0.93; the cache-heavy agent loop costs $0.02 and $3.90. o1 does not fit this workload in one request. o1 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, GPT-5.6 Luna or o1?

GPT-5.6 Luna has the larger documented context window: 1.05M, compared with 200K.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence37 rows

Agentic

  • Terminal-Bench 4.1

    GPT-5.6 Luna17.60%
    Source
    o1—

    Not directly comparable

  • Terminal-Bench 3.0

    GPT-5.6 Luna14.3%
    Source
    o1—

    Not directly comparable

  • Terminal-Bench 2.1

    GPT-5.6 Luna84.7%
    Source
    o1—

    Not directly comparable

  • BrowseComp

    GPT-5.6 Luna83.3%
    Source
    o1—

    Not directly comparable

  • OSWorld 2.0

    GPT-5.6 Luna45.6%
    Source
    o1—

    Not directly comparable

  • CyberGym

    GPT-5.6 Luna77.9%
    Source
    o1—

    Not directly comparable

  • ExploitGym

    GPT-5.6 Luna12.4%
    Source
    o1—

    Not directly comparable

  • Toolathlon

    GPT-5.6 Luna53.4%
    Source
    o1—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    GPT-5.6 Luna79.0%
    Source
    o1—

    Not directly comparable

  • ApprenticeBench

    GPT-5.6 Luna7%
    Source
    o1—

    Not directly comparable

  • MazeBench

    GPT-5.6 Luna0%
    Source
    o1—

    Not directly comparable

Coding

  • SWE-bench Pro

    GPT-5.6 Luna62.7%
    Source
    o1—

    Not directly comparable

  • Terminal-Bench 2.1

    GPT-5.6 Luna84.7%
    Source
    o1—

    Not directly comparable

  • DeepSWE

    GPT-5.6 Luna67.2%
    Source
    o1—

    Not directly comparable

  • FrontierCode 1.1 Extended

    GPT-5.6 Luna55.1%
    Source
    o1—

    Not directly comparable

  • CursorBench 3.2

    GPT-5.6 Luna61.1%
    Source
    o1—

    Not directly comparable

  • VulcanBench v3

    GPT-5.6 Luna85.5%
    Source
    o1—

    Not directly comparable

  • SWE-bench (Vals)

    GPT-5.6 Luna93.0%
    Source
    o1—

    Not directly comparable

  • CursorBench 4.0

    GPT-5.6 Luna35.9%
    Source
    o1—

    Not directly comparable

Reasoning

  • ARC-AGI-2

    GPT-5.6 Luna59.5%
    Source
    o1—

    Not directly comparable

  • ARC-AGI-3

    GPT-5.6 Luna0.2%
    Source
    o1—

    Not directly comparable

  • ARC-AGI-1

    GPT-5.6 Luna88.00%
    Source
    o1—

    Not directly comparable

Multimodal

  • ExtractBench (LlamaIndex)

    GPT-5.6 Luna91.16%
    Source
    o1—

    Not directly comparable

  • ParseBench

    GPT-5.6 Luna66.86%
    Source
    o1—

    Not directly comparable

  • MMMU-Pro

    GPT-5.6 Luna78.4%
    Source
    o1—

    Not directly comparable

  • MMMU-Pro w/ Python

    GPT-5.6 Luna79.5%
    Source
    o1—

    Not directly comparable

Knowledge

  • GPQA

    GPT-5.6 Luna92.3%
    Source
    o175.7%
    Source

    GPT-5.6 Luna leads this result

  • GPQA-D

    GPT-5.6 Luna92.3%
    Source
    o1—

    Not directly comparable

  • HealthBench Professional

    GPT-5.6 Luna55.7%
    Source
    o1—

    Not directly comparable

  • HealthBench Hard

    GPT-5.6 Luna32.0%
    Source
    o1—

    Not directly comparable

  • GPQA Diamond (Vals)

    GPT-5.6 Luna91.7%
    Source
    o1—

    Not directly comparable

  • MMLU-Pro (Vals)

    GPT-5.6 Luna86.0%
    Source
    o1—

    Not directly comparable

  • MMLU

    GPT-5.6 Luna—
    o191.8%
    Source

    Not directly comparable

Instruction following

  • IFEval

    GPT-5.6 Luna—
    o192.2%
    Source

    Not directly comparable

Math

  • FrontierMath (legacy)

    GPT-5.6 Luna78.6%
    Source
    o1—

    Not directly comparable

  • FrontierMath v2 (Tiers 1-3)

    GPT-5.6 Luna78.600%
    Source
    o114.737%
    Source

    GPT-5.6 Luna leads this result

  • FrontierMath v2 (Tier 4)

    GPT-5.6 Luna58.500%
    Source
    o1—

    Not directly comparable

37 public results · 2 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch GPT-5.6 Luna vs o1

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 7,000+ subscribers.

Last updated November 10, 2026