Claude Opus 4.8 vs GPT-5.5
Anthropic Claude Opus 4.8 | OpenAI GPT-5.5 | |
|---|---|---|
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | May 28 2026 | Apr 23 2026 |
| Access | Proprietary | Proprietary |
| Specifications | ||
Context window | 1M | 1.05M |
| 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%Best | 47% |
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 | 58.6% |
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 | 77.8% |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | 63.8% | 64.3%Best |
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% | 64.3%Best |
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% | — |
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% | 78.2%Best |
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. | — | 82.7% |
Software engineering Expert-SWE (Internal)OpenAI's private set of expert-level software-engineering problems. Higher is better. | — | 73.1% |
Multi-step tool use MCP AtlasCan the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. | — | 75.3% |
General tool use ToolathlonTests how well the AI uses everyday real-world tools and apps to get things done. Higher is better. | — | 55.6% |
Web browsing BrowseCompCan the AI browse the web and track down hard-to-find answers? Higher is better. | — | 84.4% |
Cybersecurity CyberGymTests the AI on cybersecurity challenges — finding and exploiting software weaknesses inside a safe sandbox. Higher is better. | — | 81.8% |
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%Best | 41.4% |
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%Best | 52.2% |
Abstract reasoning ARC-AGI-2Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | — | 84.6% |
Advanced math FrontierMath · Tier 1–3Very hard, research-level math problems. Tiers 1–3 are the (still extremely difficult) lower tiers. Higher is better. | — | 51.7% |
Advanced math FrontierMath · Tier 4Very hard, research-level math problems. Tier 4 is the hardest — close to what professional research mathematicians tackle. Higher is better. | — | 35.4% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 93.6% |
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%Best | 78.7% |
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%Best | 51.8% |
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%Best | 3.75% |
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%Best | 74.98% |
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% | 86.87%Best |
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. | 1890Best | 1769 |
Knowledge work GDPval (win/tie rate)How often the AI's work matches or beats a human expert's on real knowledge-work tasks. Higher is better. | — | 84.9% |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 84.1% |
Multimodal reasoning MMMU-ProA tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 81.2% |
Spatial reasoning Blueprint-Bench 2Can the AI reason about space and layout — for example, understanding a floor plan or blueprint? Higher is better. | — | 36.2% |
Long context MRCR v2 (8-needle) · 128k averageTests whether the AI can find specific details buried inside a very long document (around 128k tokens — roughly a long book). Higher is better. | — | 94.8% |
| Timeline | ||
| Release gap | GPT-5.5 shipped 35 days before Claude Opus 4.8 | |
Which is better: Claude Opus 4.8 or GPT-5.5?
Claude Opus 4.8 leads GPT-5.5 on 10 of the 14 benchmarks they both report. GPT-5.5 shipped 35 days before Claude Opus 4.8, so benchmark comparisons should account for the intervening progress.
Context windows are 1M (Claude Opus 4.8) vs 1.05M (GPT-5.5).
On BullshitBench v2, Claude Opus 4.8 leads at 95% vs GPT-5.5 at 47%. On SWE-Bench Pro, Claude Opus 4.8 leads at 69.2% vs GPT-5.5 at 58.6%. On SWE-Bench Multilingual, Claude Opus 4.8 leads at 84.4% vs GPT-5.5 at 77.8%. On CursorBench v3.1, GPT-5.5 leads at 64.3% vs Claude Opus 4.8 at 63.8%. On DeepSWE 1.0, GPT-5.5 leads at 64.3% vs Claude Opus 4.8 at 55.8%. On Terminal-Bench 2.1, GPT-5.5 leads at 78.2% vs Claude Opus 4.8 at 74.6%. On Humanity's Last Exam · no tools, Claude Opus 4.8 leads at 49.8% vs GPT-5.5 at 41.4%. On Humanity's Last Exam · with tools, Claude Opus 4.8 leads at 57.9% vs GPT-5.5 at 52.2%. On OSWorld-Verified, Claude Opus 4.8 leads at 83.4% vs GPT-5.5 at 78.7%. On Finance Agent v2, Claude Opus 4.8 leads at 53.9% vs GPT-5.5 at 51.8%. On Harvey's Legal Agent Benchmark, Claude Opus 4.8 leads at 9.58% vs GPT-5.5 at 3.75%. On TaxEval v2, Claude Opus 4.8 leads at 75.63% vs GPT-5.5 at 74.98%. On MedScribe, GPT-5.5 leads at 86.87% vs Claude Opus 4.8 at 85.75%. On GDPval-AA, Claude Opus 4.8 leads at 1890 vs GPT-5.5 at 1769.
Frequently asked questions
Claude Opus 4.8 was released by Anthropic on May 28 2026.
GPT-5.5 was released by OpenAI on Apr 23 2026.
Claude Opus 4.8 leads on SWE-Bench Pro — Claude Opus 4.8 69.2% vs GPT-5.5 58.6%.
Claude Opus 4.8 leads on Humanity's Last Exam · no tools — Claude Opus 4.8 49.8% vs GPT-5.5 41.4%.
Claude Opus 4.8 has a 1M context window; GPT-5.5 has 1.05M.