Claude Fable 5.1vsGPT-5.6 Luna
Claude Fable 5.1 | GPT-5.6 Luna | |
|---|---|---|
| Specifications | ||
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | 1M | — |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $10.00 | $0.20 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | $50.00 | $1.20 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | $0.25 | $0.02 |
Cheapest inputLowest input rate across third-party providers, excluding the lab itself. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | — | $0.20Azure |
Cheapest outputLowest output rate across third-party providers, excluding the lab itself. May come from a different provider than the cheapest input. | — | $1.20Azure |
| Benchmarks | ||
Terminal-Bench 4.0Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Version 4.0 recalibrated how much time, CPU and memory each task gets, removed eight tasks and fixed nineteen, so fewer runs fail for reasons that have nothing to do with the model. Scores are not comparable with earlier versions. Higher is better. | 55.8% | 17.27% |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | 90% | 59.54% |
| BenchmarksPublished by one model only | ||
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | — | 40% |
Gray Swan IPI · k = 1Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. Gray Swan's indirect prompt injection benchmark measures how often such an attack succeeds when the attacker gets a single try. Lower is better. | — | 8.3% |
Gray Swan IPI · k = 10Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 10 tries and counts an attack as successful if any of them works. Lower is better. | — | 38.6% |
Gray Swan IPI · k = 15Prompt injection robustness — Attackers hide malicious instructions inside content the AI reads — a web page, an email, a document — and try to hijack what it does. This variant gives the attacker 15 tries and counts an attack as successful if any of them works. Lower is better. | — | 43.9% |
SWE-Bench ProAgentic coding — Can the AI fix real bugs in real software? It's handed actual problems from open-source projects and has to write code that genuinely solves them. Higher is better. | 81.2% | — |
SWE-Bench MultilingualMultilingual coding — Like SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | 89.1% | — |
SWE-Bench MultimodalMultimodal coding — Real bug reports that arrive with pictures attached — a screenshot, a mockup, a page rendering wrongly — so the AI has to read the image as well as the code to work out what to fix. Higher is better. | 54.7% | — |
Frontier-Bench v0.1Agentic computer work — A hard, ever-evolving set of real computer tasks — coding, system administration, data work, and more — that an AI agent has to complete on its own. Run by the Harbor / Laude Institute team as the successor to Terminal-Bench (v0.1 is the first release of the task set). The score is the share of tasks solved. Higher is better. | — | 14.3% |
Terminal-Bench 2.1Agentic terminal coding — Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better. | — | 82.5% |
Terminal-Bench-Science 0.1Agentic scientific computing — The same command-line setup as Terminal-Bench, pointed at scientific work: the AI has to drive research tooling and computational workflows through to a result, rather than administer a machine. Version 0.1 is the first release of the task set, and scores run lower than on the general board. Higher is better. | 52.6% | — |
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better. | — | 83.3% |
Humanity's Last Exam · no toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects, written so you can't just look up the answer. “No tools” means the AI answers on its own. Higher is better. | 60.9% | — |
Humanity's Last Exam · with toolsMultidisciplinary reasoning — Humanity's Last Exam — extremely hard expert questions across many subjects. “With tools” means the AI is allowed to search the web or run code while answering. Higher is better. | 65% | — |
AutomationBenchBusiness workflows — Tests whether the AI can run real multi-step business workflows — the kind of end-to-end office processes companies want to automate — from start to finish. Higher is better. | 31.4% | — |
HealthBench ProfessionalHealth — Realistic health conversations graded against detailed rubrics written by physicians — can the AI respond the way a careful medical professional would? Higher is better. | 62.1% | — |
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo) | 1853 | — |
AA-BriefcaseKnowledge work — Artificial Analysis agentic office-work eval (Elo) | 1694 | — |
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Sep 1 2026 | Jun 26 2026 |
| Access | Proprietary | Proprietary |
Other comparisons
Claude Fable 5.1vsGemini 3.7 FlashGPT-5.6 LunavsGemini 3.7 FlashClaude Fable 5.1vsMuse GlimmerGPT-5.6 LunavsMuse GlimmerClaude Fable 5.1vsGrok 4.6GPT-5.6 LunavsGrok 4.6Claude Fable 5.1vsDeepSeek-V4-Pro-0813GPT-5.6 LunavsDeepSeek-V4-Pro-0813Claude Fable 5.1vsMistral Medium 3.5GPT-5.6 LunavsMistral Medium 3.5Claude Fable 5.1vsKimi K3GPT-5.6 LunavsKimi K3
Frequently asked questions
Claude Fable 5.1 leads GPT-5.6 Luna on 2 of the 2 benchmarks they both report (Terminal-Bench 4.0, ARC-AGI-2). GPT-5.6 Luna is cheaper on both input and output: $0.20 vs $10.00 per million input tokens, and $1.20 vs $50.00 per million output tokens. Figures are base-tier rates. GPT-5.6 Luna shipped 67 days before Claude Fable 5.1, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On Terminal-Bench 4.0, Claude Fable 5.1 leads at 55.8% vs GPT-5.6 Luna at 17.27%. On ARC-AGI-2, Claude Fable 5.1 leads at 90% vs GPT-5.6 Luna at 59.54%.
Claude Fable 5.1 was released by Anthropic on Sep 1 2026.
GPT-5.6 Luna was released by OpenAI on Jun 26 2026.
Claude Fable 5.1 leads on Terminal-Bench 4.0 — Claude Fable 5.1 55.8% vs GPT-5.6 Luna 17.27%.
Claude Fable 5.1 leads on ARC-AGI-2 — Claude Fable 5.1 90% vs GPT-5.6 Luna 59.54%.
GPT-5.6 Luna is cheaper on both input and output: $0.20 vs $10.00 per million input tokens, and $1.20 vs $50.00 per million output tokens. Figures are base-tier rates. Rates are pay-as-you-go API prices verified on September 1, 2026.