Claude Fable 5
Released
Claude Fable 5 is an AI model released by Anthropic on Tuesday, Jun 9 2026, 12 days after Claude Opus 4.8. It has a 1M token context window. Benchmark results (shown below) cover Next.js Evals, HealthBench Professional, GDPval-AA, BullshitBench v2, Gray Swan IPI, SWE-Bench Pro, and 17 more.
API pricing
- InputWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it.
- $10.00
- Cached inputA 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.
- $1.00
- 5 min cache writeA one-off charge for storing text so later requests can reuse it at the cheaper cached rate. This option keeps it for five minutes.
- $12.50
- 1 hr cache writeA one-off charge for storing text so later requests can reuse it at the cheaper cached rate. This option keeps it for an hour, so it costs more than the five-minute one.
- $20.00
- OutputWhat 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
Available from
| Amazon Bedrock | — | $10.00 | $50.00 | 1M |
|---|---|---|---|---|
| Azure | — | $10.00 | $50.00 | 1M |
| global | $10.00 | $50.00 | 1M | |
| eu | $11.00 | $55.00 | 1M |
Benchmarks
Coding
Next.js EvalsNext.js coding — Vercel's open eval of how well AI coding agents build and migrate real Next.js apps — measured as the share of tasks the agent completes successfully. Higher is better.
92%
#1Best published Next.js score of all tracked models
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.
80.3%
#2 of 23Best: Claude Fable 5.1 · 81.2%
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better.
95.5%
#2 of 57Best: Claude Opus 5 · 96%
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.
86.6%
#3 of 14Best: Claude Opus 5 · 89.5%
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.
54.1%
#3 of 3Best: Claude Opus 5 · 59.4%
DeepSWE 1.1Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. (Version 1.1 of the test.) Higher is better.
70%
#5 of 25Best: Muse Spark 1.3 · 75.4%
DeepSWE 1.0Agentic coding — Artificial Analysis' independent test of deep, agentic software-engineering work — the AI has to plan and carry out substantial coding tasks end to end. Higher is better.
66.1%
#2 of 6Best: Kimi K3 · 67.5%
Terminal & CLI
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.
33.8%
#3 of 9Best: Claude Opus 5 · 43.3%
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.
44.55%
via Terminal-Bench
#5 of 15Best: Claude Mythos 5.1 · 60.9%
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.
88%
#6 of 29Best: Gemini 3.8 Flash · 89.4%
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.
24.7%
#4 of 4Best: GPT-6 Astra · 64.6%
Agentic & tool use
BrowseCompWeb browsing — Can the AI browse the web and track down hard-to-find answers? Higher is better.
86.9%
via BenchLM
#9 of 28Best: GPT-5.6 Sol · 92.2%
OSWorld-VerifiedAgentic computer use — Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better.
85%
#2 of 28Best: Qwen3.8-Max · 86.1%
Reasoning & science
Humanity's Last ExamMultidisciplinary 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.
#3 of 41Best: Claude Fable 5.1 · 65%
Knowledge work
GDPval-AAKnowledge work — Measures how well the AI does economically valuable knowledge work, judged against human experts. Shown as a rating (like a chess Elo) — higher is better.
1932
#1Best published GDPval score of all tracked models
GDPval-AA v2Knowledge work — economically valuable knowledge work (v2, re-based Elo)
1760
#5 of 20Best: Claude Opus 5 · 1861
Legal & tax
Harvey's Legal Agent BenchmarkAgentic legal work — Harvey's test of whether an AI agent can complete real legal work — drafting and reviewing documents, working with spreadsheets and presentations, and navigating files the way a lawyer's assistant would. Higher is better.
11.25%
#4 of 8Best: Muse Spark 1.1 · 20%
TaxEval v2Tax questions — A set of real tax questions created by Vals AI — can the AI give accurate answers about tax rules and filings? Higher is better.
76.94%
#2 of 4Best: Muse Spark 1.1 · 79.72%
Healthcare
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.
63.3%
#1Best published HealthBench Pro score of all tracked models
MedScribeMedical admin work — Can the AI support doctors with their administrative work, like notes and paperwork? Created by Vals AI. Higher is better.
88.52%
#2 of 5Best: Muse Spark 1.1 · 88.89%
Robustness
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.
54%
#20 of 74Best: Claude Opus 4.8 · 95%
Gray Swan IPIPrompt 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.
0.4%
k = 1
2.3%
k = 10
2.8%
k = 15
k = 1
#2 of 13Best: Claude Opus 5 · 0.2%
k = 10
#2 of 13Best: Claude Opus 5 · 1.6%
k = 15
#2 of 13Best: Claude Opus 5 · 2%
Community preference
threejsevalCommunity preference (Three.js) — Every model gets the same prompt — "the Eiffel Tower", "a glass fishbowl", "a robot arm picking toys into a box" — and builds a 3D scene in Three.js. Real people then see two scenes side by side, names hidden, and vote for the one they prefer. The votes become a chess-style Elo rating on threejseval.com, averaged across all the prompts. It measures whether the scene looks and moves right to a human eye, not whether the code passes a test. Higher is better.
1552
#5 of 16Best: Claude Fable 5.1 · 2037
Source: Terminal-Bench, retrieved 30 August 2026 · Source: BenchLM, retrieved 11 July 2026. Every other score here is the figure the lab published at launch.
About
Claude Fable 5, released June 9, 2026, is the first model of Anthropic's Claude 5 generation and the debut of the Mythos-class tier that sits above Opus in the lineup. It posted the largest single-release jump in the tracker's dataset: 95.5% on SWE-Bench Verified, 80.3% on SWE-Bench Pro, 88.0% on Terminal-Bench 2.1, and a WebDev Arena coding Elo of 1649 — over 80 points clear of the next model at launch.
Fable 5 ships with a 1M-token context window and leads agentic evaluations including OSWorld-Verified (85.0%) and Artificial Analysis GDPval (1932 Elo). The same underlying model without those additional dual-use safety measures shipped the same day as Claude Mythos 5, for vetted organisations only. Claude Sonnet 5 followed on June 30, 2026, and Claude Opus 5 brought the 5-series to the Opus tier on July 24, 2026 at half Fable's price. Fable 5 held the top of the lineup for twelve weeks, until Claude Fable 5.1 succeeded it on September 1, 2026 at the same price.
Compare Claude Fable 5 with
Suggested comparisons
Claude Fable 5vsClaude Fable 5.1Claude Fable 5vsGPT-6 AstraClaude Fable 5vsGemini 3.8 FlashClaude Fable 5vsMuse Spark 1.3Claude Fable 5vsGrok 4.6Claude Fable 5vsDeepSeek-V4-Pro-0813Claude Fable 5vsMistral Medium 3.5Claude Fable 5vsKimi K3Claude Fable 5vsGLM-5.3-FlashClaude Fable 5vsQwen3.8-Max-0902Claude Fable 5vsNemotron 3.5 Lightning
Frequently asked questions
Claude Fable 5 was released by Anthropic on Tuesday, Jun 9 2026.