Claude Sonnet 4vsClaude Sonnet 4.6
Claude Sonnet 4 | Claude Sonnet 4.6 | |
|---|---|---|
| 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. | 30% | 91%Best |
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. | 72.7% | 79.6%Best |
Agentic coding CursorBench v3.1Cursor's own test of harder, real-world coding tasks inside a code editor. Higher is better. | — | 49% |
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. | — | 30% |
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. | — | 58% |
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% |
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. | — | 62% |
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. | — | 33.2% |
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. | — | 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. | 75.4% | 89.9%Best |
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. | — | 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. | — | 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. | — | 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% |
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. | — | 1472 |
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. | — | 1521 |
| Overview | ||
| Company | Anthropic | Anthropic |
| Release date | May 22 2025 | Feb 17 2026 |
| Access | Proprietary | Proprietary |
Which is better: Claude Sonnet 4 or Claude Sonnet 4.6?
Claude Sonnet 4.6 leads Claude Sonnet 4 on 3 of the 3 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, GPQA Diamond). Claude Sonnet 4 shipped 271 days before Claude Sonnet 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 BullshitBench v2, Claude Sonnet 4.6 leads at 91% vs Claude Sonnet 4 at 30%. On SWE-Bench Verified, Claude Sonnet 4.6 leads at 79.6% vs Claude Sonnet 4 at 72.7%. On GPQA Diamond, Claude Sonnet 4.6 leads at 89.9% vs Claude Sonnet 4 at 75.4%.
Frequently asked questions
Claude Sonnet 4 was released by Anthropic on May 22 2025.
Claude Sonnet 4.6 was released by Anthropic on Feb 17 2026.
Claude Sonnet 4.6 leads on SWE-Bench Verified — Claude Sonnet 4 72.7% vs Claude Sonnet 4.6 79.6%.
Claude Sonnet 4.6 leads on GPQA Diamond — Claude Sonnet 4 75.4% vs Claude Sonnet 4.6 89.9%.
Other comparisons
Claude Sonnet 4vsGPT-5.6-CyberClaude Sonnet 4.6vsGPT-5.6-CyberClaude Sonnet 4vsGemini 3.7 FlashClaude Sonnet 4.6vsGemini 3.7 FlashClaude Sonnet 4vsMuse GlimmerClaude Sonnet 4.6vsMuse GlimmerClaude Sonnet 4vsGrok 4.6Claude Sonnet 4.6vsGrok 4.6Claude Sonnet 4vsDeepSeek-V4-Pro-0813Claude Sonnet 4.6vsDeepSeek-V4-Pro-0813Claude Sonnet 4vsMistral Medium 3.5Claude Sonnet 4.6vsMistral Medium 3.5