Claude Fable 5vsComposer 2.5
Claude Fable 5 | Composer 2.5 | |
|---|---|---|
| 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%Best | 54% |
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% | — |
Multilingual coding SWE-Bench MultilingualLike SWE-Bench, but the coding problems span many programming languages, not just one. Tests how broadly the AI can code. Higher is better. | — | 79.8% |
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 | 56.1% |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | 72.9%Best | 63.2% |
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% | — |
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%Best | 18% |
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% | 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 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%Best | 73% |
Agentic terminal coding Terminal-Bench 2.0Can the AI work in a command-line terminal — running commands and finishing technical setup tasks the way a developer would? (Version 2.0 of the test.) Higher is better. | — | 69.3% |
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% | — |
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% | — |
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) | 1760 | — |
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 | May 18 2026 |
| Access | Proprietary | Proprietary |
Which is better: Claude Fable 5 or Composer 2.5?
Claude Fable 5 leads Composer 2.5 on 5 of the 6 benchmarks they both report. Composer 2.5 shipped 22 days before Claude Fable 5, 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 SWE-Bench Pro, Claude Fable 5 leads at 80.3% vs Composer 2.5 at 54%. On CursorBench v3.2, Claude Fable 5 leads at 70.5% vs Composer 2.5 at 56.1%. On CursorBench v3.1, Claude Fable 5 leads at 72.9% vs Composer 2.5 at 63.2%. On DeepSWE 1.0, Claude Fable 5 leads at 66.1% vs Composer 2.5 at 18%. On Next.js Evals, both models score 92%. On Terminal-Bench 2.1, Claude Fable 5 leads at 88% vs Composer 2.5 at 73%.
Frequently asked questions
Claude Fable 5 was released by Anthropic on Jun 9 2026.
Composer 2.5 was released by SpaceXAI on May 18 2026.
Claude Fable 5 leads on SWE-Bench Pro — Claude Fable 5 80.3% vs Composer 2.5 54%.
Other comparisons
Claude Fable 5vsGPT-5.6-CyberComposer 2.5vsGPT-5.6-CyberClaude Fable 5vsGemini 3.7 FlashComposer 2.5vsGemini 3.7 FlashClaude Fable 5vsMuse GlimmerComposer 2.5vsMuse GlimmerClaude Fable 5vsDeepSeek-V4-Pro-0813Composer 2.5vsDeepSeek-V4-Pro-0813Claude Fable 5vsMistral Medium 3.5Composer 2.5vsMistral Medium 3.5Claude Fable 5vsKimi K3Composer 2.5vsKimi K3