4 vs 0 benchmarks won
Anthropic Claude Opus 4.8 | Anthropic Claude Sonnet 4.6 | |
|---|---|---|
| Overview | ||
| Company | Anthropic | Anthropic |
| Release date | May 28 2026 | Feb 17 2026 |
| Model type | — | — |
| Open source | No | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| 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. | 69.2% | — |
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. | — | 79.6% |
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% | — |
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. | — | 69.5% |
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 | 33.2% |
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% | — |
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. | — | 58.3% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 89.9% |
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%Best | 72.5% |
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% |
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 | 1676 |
Chart reasoning CharXiv ReasoningCan the AI read and reason about complex charts and figures, not just text? Higher is better. | — | 72.4% |
Multimodal reasoning MMMU-ProA tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. | — | 74.5% |
Spatial reasoning Blueprint-Bench 2Can the AI reason about space and layout — for example, understanding a floor plan or blueprint? Higher is better. | — | 6.7% |
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. | — | 84.9% |
| Timeline | ||
| Release gap | Claude Sonnet 4.6 shipped 100 days before Claude Opus 4.8 | |
Claude Opus 4.8 leads Claude Sonnet 4.6 on 4 of the 4 benchmarks they both report (Humanity's Last Exam, OSWorld-Verified, Finance Agent v2, GDPval-AA). Claude Sonnet 4.6 shipped 100 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 Humanity's Last Exam · no tools, Claude Opus 4.8 leads at 49.8% vs Claude Sonnet 4.6 at 33.2%. On OSWorld-Verified, Claude Opus 4.8 leads at 83.4% vs Claude Sonnet 4.6 at 72.5%. On Finance Agent v2, Claude Opus 4.8 leads at 53.9% vs Claude Sonnet 4.6 at 51%. On GDPval-AA, Claude Opus 4.8 leads at 1890 vs Claude Sonnet 4.6 at 1676.