Skip to content
ModelCap

Head-to-head comparison

Claude Fable 5.1 vs GPT-5.6 Luna

Claude Fable 5.1 (Anthropic) and GPT-5.6 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 3 September 2026

As of 3 September 2026, Claude Fable 5.1 holds the stronger ModelCap Index position (#2 vs #18); and GPT-5.6 Luna is 41.7× cheaper per output token ($1.20/1M vs $50.00/1M).

Which should you choose?

Choose Claude Fable 5.1 if…

  • you want the stronger overall ModelCap Index position — #2 against #18 (84.1 vs 69.7 points).
  • you want provider choice — 4 listed API providers against 3.
  • ARC-AGI-2 is your yardstick — 90.0% against 59.6%.
  • AA Intelligence Index is your yardstick — 65.7 against 52.3.
  • AA Terminal-Bench 2.1 is your yardstick — 91.4% against 80.9%.
  • AA Humanity's Last Exam is your yardstick — 59.1% against 39.5%.
  • you want the more recently listed model — Claude Fable 5.1 was listed 1 September 2026, GPT-5.6 Luna 9 July 2026.

Choose GPT-5.6 Luna if…

  • API cost matters — $1.20/1M output tokens against $50.00/1M, about 41.7× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.20/1M against $10.00/1M.

Claude Fable 5.1 vs GPT-5.6 Luna: specs, pricing and context

Specification comparison of Claude Fable 5.1 and GPT-5.6 Luna
FieldClaude Fable 5.1AnthropicGPT-5.6 LunaOpenAI
ModelCap Index position#2#18
Index score84.169.7
EvidenceMeasuredMeasured
Input price / 1M tokens$10.00$0.20
Output price / 1M tokens$50.00$1.20
Context window1M tokens1M tokens
Max output tokens128K128K
API providers listed43
Weight accessAPI onlyAPI only
Input modalitiesText, Image, FileFile, Image, Text
First listed1 September 20269 July 2026
PublisherAnthropicOpenAI

Evidence: 2 public benchmark observations across 2 boards · 6 public benchmark observations across 6 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Claude Fable 5.1 vs GPT-5.6 Luna

Public benchmark boards where Claude Fable 5.1 or GPT-5.6 Luna has a published result
BoardClaude Fable 5.1GPT-5.6 LunaLeads
Arena codingArena (LMArena)—14971489–1505X-HighOnly one result
LMArena AgentLMArena—2.1%0.9%–3.4%X-HighOnly one result
ARC-AGI-2ARC Prize Foundation90.0%Max59.6%MaxClaude Fable 5.1
ARC-AGI-3ARC Prize Foundation—0.2%MaxOnly one result
AA Intelligence IndexArtificial Analysis65.7intelligence-index52.3intelligence-indexClaude Fable 5.1
AA Terminal-Bench 2.1Artificial Analysis91.4%terminal-bench-2.180.9%terminal-bench-2.1Claude Fable 5.1
AA Humanity's Last ExamArtificial Analysis59.1%humanitys-last-exam39.5%humanitys-last-examClaude Fable 5.1
Terminal-Bench 4.0Terminal-Bench (Laude Institute)—17.3%14.4%–20.1%Codex · MaxOnly 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.

Claude Fable 5.1 vs GPT-5.6 Luna: common questions

Is Claude Fable 5.1 better than GPT-5.6 Luna?

Claude Fable 5.1 ranks higher on the ModelCap Index as of 3 September 2026: #2 against #18. 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.

Is Claude Fable 5.1 cheaper than GPT-5.6 Luna?

GPT-5.6 Luna is cheaper on output tokens: $1.20/1M against $50.00/1M. Input tokens are $10.00/1M for Claude Fable 5.1 and $0.20/1M for GPT-5.6 Luna. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens.

Which has the bigger context window, Claude Fable 5.1 or GPT-5.6 Luna?

Both publish a 1M-token context window.

Which is better for coding, Claude Fable 5.1 or GPT-5.6 Luna?

AA Terminal-Bench 2.1: Claude Fable 5.1 91.4%, GPT-5.6 Luna 80.9% — Claude Fable 5.1 leads.

Are Claude Fable 5.1 and GPT-5.6 Luna open-weight models?

Claude Fable 5.1: API only. GPT-5.6 Luna: API only. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.

Where can I run Claude Fable 5.1 and GPT-5.6 Luna?

ModelCap currently lists 4 API providers for Claude Fable 5.1 and 3 for GPT-5.6 Luna, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Claude Fable 5.1 vs GPT-5.6 Luna comparison?

Every figure comes from the sealed ModelCap dataset published 3 September 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.

Explore further