Claude Fable 5vsGrok 4.6
Claude Fable 5 | Grok 4.6 | |
|---|---|---|
| Specifications | ||
Context window | 1M | — |
| Benchmarks | ||
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% | — |
Prompt injection robustness Gray Swan IPI · k = 1Attackers 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% | — |
Prompt injection robustness Gray Swan IPI · k = 10Attackers 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. | 2.3% | — |
Prompt injection robustness Gray Swan IPI · k = 15Attackers 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. | 2.8% | — |
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% | — |
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% | — |
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%Best | 69.9% |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | 72.9% | — |
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%Best | 65.9% |
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% | — |
Agentic coding FrontierCode v1.1 (Extended) · extended splitfrontier-difficulty agentic coding tasks (v1.1, extended split) | — | 61.3% |
Expert software engineering APEX-SWEexpert-level software-engineering tasks (AI Productivity Index) | — | 56.4% |
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% | — |
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% | — |
Agentic terminal coding Terminal-Bench 3.0command-line task completion (v3.0, much harder task set) | — | 26% |
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% | — |
Expert agentic work APEX-Agentsexpert-level agentic work tasks (AI Productivity Index) | — | 57.5% |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | 86.9% | — |
Multidisciplinary reasoning Humanity's Last Exam · with toolsHumanity'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% | — |
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% | — |
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% | 15.8%Best |
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% | — |
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% | — |
Overall intelligence AA Intelligence IndexArtificial Analysis composite intelligence index across evals | — | 61 |
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 | — |
Knowledge work GDPval-AA v2economically valuable knowledge work (v2, re-based Elo) | 1760Best | 1753 |
Knowledge work AA-BriefcaseArtificial Analysis agentic office-work eval (Elo) | — | 1577 |
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 | — |
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 | — |
| Overview | ||
| Company | Anthropic | SpaceXAI |
| Release date | Jun 9 2026 | Aug 12 2026 |
| Access | Proprietary | Proprietary |
Which is better: Claude Fable 5 or Grok 4.6?
Claude Fable 5 leads Grok 4.6 on 3 of the 4 benchmarks they both report (CursorBench v3.2, DeepSWE 1.1, Harvey's Legal Agent Benchmark, GDPval-AA v2). Claude Fable 5 shipped 64 days before Grok 4.6, 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 CursorBench v3.2, Claude Fable 5 leads at 70.5% vs Grok 4.6 at 69.9%. On DeepSWE 1.1, Claude Fable 5 leads at 70% vs Grok 4.6 at 65.9%. On Harvey's Legal Agent Benchmark, Grok 4.6 leads at 15.8% vs Claude Fable 5 at 11.25%. On GDPval-AA v2, Claude Fable 5 leads at 1760 vs Grok 4.6 at 1753.
Frequently asked questions
Claude Fable 5 was released by Anthropic on Jun 9 2026.
Grok 4.6 was released by SpaceXAI on Aug 12 2026.
Claude Fable 5 leads on CursorBench v3.2 — Claude Fable 5 70.5% vs Grok 4.6 69.9%.
Other comparisons
Claude Fable 5vsGPT-5.6-CyberGrok 4.6vsGPT-5.6-CyberClaude Fable 5vsGemini 3.6 FlashGrok 4.6vsGemini 3.6 FlashClaude Fable 5vsMuse GlimmerGrok 4.6vsMuse GlimmerClaude Fable 5vsDeepSeek-V4-Flash-0731Grok 4.6vsDeepSeek-V4-Flash-0731Claude Fable 5vsMistral Medium 3.5Grok 4.6vsMistral Medium 3.5Claude Fable 5vsKimi K3Grok 4.6vsKimi K3