Claude Opus 4.8vsComposer 2.5
Claude Opus 4.8 | 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. | 95% | — |
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. | 0.5% | — |
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. | 4.1% | — |
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. | 5.5% | — |
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. | 69.2%Best | 54% |
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. | 84.4%Best | 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. | 62.3%Best | 56.1% |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | 63.8%Best | 63.2% |
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. | 55.8%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. | 88% | 92%Best |
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. | 21.1% | — |
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. | 74.6%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% |
Browser agent BU BenchCan the AI drive a real web browser to finish tasks — clicking, filling forms, and navigating sites the way a person would? Run by Browser Use on their BU Bench task set. Higher is better. | 74% | — |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | 84.3% | — |
Multidisciplinary reasoning Humanity's Last Exam · no toolsHumanity'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. | 49.8% | — |
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. | 57.9% | — |
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. | 83.4% | — |
Agentic financial analysis Finance Agent v2Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better. | 53.9% | — |
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. | 9.58% | — |
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. | 75.63% | — |
Medical admin work MedScribeCan the AI support doctors with their administrative work, like notes and paperwork? Created by Vals AI. Higher is better. | 85.75% | — |
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. | 1890 | — |
Knowledge work GDPval-AA v2economically valuable knowledge work (v2, re-based Elo) | 1600 | — |
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. | 1482 | — |
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. | 1568 | — |
| Overview | ||
| Company | Anthropic | SpaceXAI |
| Release date | May 28 2026 | May 18 2026 |
| Access | Proprietary | Proprietary |
Which is better: Claude Opus 4.8 or Composer 2.5?
Claude Opus 4.8 leads Composer 2.5 on 6 of the 7 benchmarks they both report. Composer 2.5 shipped 10 days before Claude Opus 4.8, 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 Opus 4.8 leads at 69.2% vs Composer 2.5 at 54%. On SWE-Bench Multilingual, Claude Opus 4.8 leads at 84.4% vs Composer 2.5 at 79.8%. On CursorBench v3.2, Claude Opus 4.8 leads at 62.3% vs Composer 2.5 at 56.1%. On CursorBench v3.1, Claude Opus 4.8 leads at 63.8% vs Composer 2.5 at 63.2%. On DeepSWE 1.0, Claude Opus 4.8 leads at 55.8% vs Composer 2.5 at 18%. On Next.js Evals, Composer 2.5 leads at 92% vs Claude Opus 4.8 at 88%. On Terminal-Bench 2.1, Claude Opus 4.8 leads at 74.6% vs Composer 2.5 at 73%.
Frequently asked questions
Claude Opus 4.8 was released by Anthropic on May 28 2026.
Composer 2.5 was released by SpaceXAI on May 18 2026.
Claude Opus 4.8 leads on SWE-Bench Pro — Claude Opus 4.8 69.2% vs Composer 2.5 54%.
Other comparisons
Claude Opus 4.8vsGPT-5.6-CyberComposer 2.5vsGPT-5.6-CyberClaude Opus 4.8vsGemini 3.7 FlashComposer 2.5vsGemini 3.7 FlashClaude Opus 4.8vsMuse GlimmerComposer 2.5vsMuse GlimmerClaude Opus 4.8vsDeepSeek-V4-Pro-0813Composer 2.5vsDeepSeek-V4-Pro-0813Claude Opus 4.8vsMistral Medium 3.5Composer 2.5vsMistral Medium 3.5Claude Opus 4.8vsKimi K3Composer 2.5vsKimi K3