Claude Fable 5
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 SWE-Bench Pro, SWE-Bench Verified, CursorBench v3.2, CursorBench v3.1, Next.js Evals, OSWorld-Verified, and 14 more.
Benchmarks
Agentic coding
SWE-Bench ProCan 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%
#1Best published SWE-Pro score of all tracked models
Coding
SWE-Bench VerifiedReal 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%
#1Best published SWE-Ver score of all tracked models
Agentic coding
CursorBench v3.2Cursor's own test of harder, real-world coding tasks inside a code editor, on the refreshed v3.2 task set. Scores aren't comparable with v3.1. Higher is better.
70.5%
#1Best published CursorBench score of all tracked models
Agentic coding
CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better.
72.9%
#1Best published CursorBench score of all tracked models
Next.js coding
Next.js EvalsVercel'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
Agentic computer use
OSWorld-VerifiedCan the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better.
85%
#1Best published OSWorld score of all tracked models
Knowledge work
GDPval-AAMeasures 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
Community preference
Arena Elo (Text)Real people chat with two anonymous AIs side by side and vote for the answer they prefer. Votes become a chess-style Elo rating on arena.ai — it measures which AI people actually like, not test scores. Higher is better.
1509
#1Best published Arena Text score of all tracked models
Nonsense detection
BullshitBench v2Given 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%
#13 of 62Best: Claude Opus 4.8 · 95%
Agentic coding
DeepSWE 1.1Artificial 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%
#2 of 13Best: GPT-5.6 Sol · 73%
Agentic coding
DeepSWE 1.0Artificial 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%
Agentic computer work
Frontier-Bench v0.1A 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%
Agentic terminal coding
Terminal-Bench 2.1Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? Higher is better.
88%
#3 of 18Best: GPT-5.6 Sol · 88.8%
Web browsing
BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better.
86.9%
#5 of 16Best: Kimi K3 · 91.2%
Multidisciplinary reasoning
Humanity's Last ExamHumanity'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.
64.5%
with tools
#2 of 17Best: Claude Opus 5 · 64.7%
Agentic legal work
Harvey's Legal Agent BenchmarkHarvey'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%
#3 of 5Best: Muse Spark 1.1 · 20%
Tax questions
TaxEval v2A 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%
Medical admin work
MedScribeCan 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%
Knowledge work
GDPval-AA v2economically valuable knowledge work (v2, re-based Elo)
1760
#2 of 11Best: Claude Opus 5 · 1861
Community preference (code)
Arena Elo (Code)Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better.
1631
#2 of 38Best: Kimi K3 · 1679
About Claude Fable 5
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). Anthropic offers the same underlying model without additional dual-use safety measures as Claude Mythos 5 to approved organisations. 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.