Skip to content
ModelCap

Head-to-head comparison

GPT-5.5 vs GPT-6 Luna

GPT-5.5 (OpenAI) and GPT-6 Luna (OpenAI) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.

Snapshot as of 6 November 2026

As of 6 November 2026, GPT-5.5 holds the stronger ModelCap Index position (#16 vs #53); and GPT-6 Luna is 60× cheaper per output token ($0.50/1M vs $30.00/1M).

Which should you choose?

Choose GPT-5.5 if…

  • you want the stronger overall ModelCap Index position — #16 against #53 (80.1 vs 67.6 points).
  • Arena text is your yardstick — 1482 against 1441.
  • Arena coding is your yardstick — 1519 against 1506.
  • ARC-AGI-2 is your yardstick — 85.0% against 59.3%.
  • ARC-AGI-3 is your yardstick — 0.4% against 0.2%.

Choose GPT-6 Luna if…

  • API cost matters — $0.50/1M output tokens against $30.00/1M, about 60× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.10/1M against $5.00/1M.
  • you want the more recently listed model — GPT-6 Luna was listed 22 September 2026, GPT-5.5 24 April 2026.

GPT-5.5 vs GPT-6 Luna: specs, pricing and context

Specification comparison of GPT-5.5 and GPT-6 Luna
FieldGPT-5.5OpenAIGPT-6 LunaOpenAI
ModelCap Index position#16#53
Index score80.167.6
EvidenceMeasuredMeasured
Input price / 1M tokens$5.00$0.10
Output price / 1M tokens$30.00$0.50
Context window1M tokens1M tokens
Declared route output cap128K128K
API providers listed33
Weight accessNo linked weightsNo linked weights
Input modalitiesFile, Image, TextFile, Image, Text
First listed24 April 202622 September 2026
PublisherOpenAIOpenAI

Evidence: 4 public benchmark observations across 4 boards · 5 public benchmark observations across 5 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: GPT-5.5 vs GPT-6 Luna

Public benchmark boards where GPT-5.5 or GPT-6 Luna has a published result
BoardGPT-5.5GPT-6 LunaLeads
Arena textArena (LMArena)14821478–1485High14411437–1445MaxGPT-5.5
Arena codingArena (LMArena)15191513–1525High15061500–1512MaxGPT-5.5
LMArena AgentLMArena—1.9%1.5%–2.3%MaxOnly one result
ARC-AGI-2ARC Prize Foundation85.0%X-High59.3%MaxGPT-5.5
ARC-AGI-3ARC Prize Foundation0.4%High0.2%MediumGPT-5.5
AA Intelligence IndexArtificial Analysis—27.9MaxOnly one result
Terminal-Bench 4.0Terminal-Bench (Laude Institute)—16.4%13.6%–19.1%Codex · MaxOnly one result
Terminal-Bench 2.1 Terminus 2Terminal-Bench78.0X-High—Only one result
WildClawBench OpenClawWildClawBench58.2—Only one result

Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.

Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.

GPT-5.5 vs GPT-6 Luna: common questions

Is GPT-5.5 better than GPT-6 Luna?

GPT-5.5 ranks higher on the ModelCap Index as of 6 November 2026: #16 against #53. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it. Their published uncertainty intervals do not overlap, but the aggregate Index does not predict performance on every task; compare the relevant benchmark configurations before choosing.

Is GPT-5.5 cheaper than GPT-6 Luna?

GPT-6 Luna is cheaper on output tokens: $0.50/1M against $30.00/1M. Input tokens are $5.00/1M for GPT-5.5 and $0.10/1M for GPT-6 Luna. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $25.00 for GPT-5.5 versus $0.45 for GPT-6 Luna. GPT-6 Luna costs 98.2% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.

Which has the bigger context window, GPT-5.5 or GPT-6 Luna?

Both publish a 1M-token context window. OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified.

Which is better for coding, GPT-5.5 or GPT-6 Luna?

Arena coding: GPT-5.5 1519, GPT-6 Luna 1506 — GPT-5.5 leads.

Are GPT-5.5 and GPT-6 Luna open-weight models?

GPT-5.5: No linked weights. GPT-6 Luna: No linked weights. Open weights mean the checkpoint can be downloaded and self-hosted under its licence. A missing weight link does not identify every API or chat product that offers a model.

Where can I run GPT-5.5 and GPT-6 Luna?

ModelCap currently lists 3 API providers for GPT-5.5 and 3 for GPT-6 Luna, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this GPT-5.5 vs GPT-6 Luna comparison?

Every figure and ModelCap Index position comes from the same published snapshot dated 6 November 2026. Publication and page updates happen separately; use the snapshot date shown on the page.

Explore further