# Claude Sonnet 4.6

Claude Sonnet 4.6 is an AI model released by Anthropic on Feb 17 2026. Tracked results include 91% on BullshitBench v2, 89.9% on GPQA Diamond and 79.6% on SWE-Bench Verified.

## Facts

| Field | Value |
| --- | --- |
| Model | Claude Sonnet 4.6 |
| Developer | Anthropic |
| Release date | Tuesday, Feb 17 2026 |
| Licensing | Proprietary |

## API pricing

All rates in USD per 1,000,000 tokens, pay-as-you-go.

| Tier | Input | Cached input | 5 min cache write | 1 hr cache write | Output |
| --- | --- | --- | --- | --- | --- |
| All documented contexts | $3.00 | $0.30 | $3.75 | $6.00 | $15.00 |

Verified August 18, 2026 against the first-party source: https://platform.claude.com/docs/en/about-claude/pricing

## Tracked benchmark scores

| Benchmark | Score | Source | What it measures |
| --- | --- | --- | --- |
| BullshitBench v2 | 91% | [BullshitBench](https://github.com/petergpt/bullshit-benchmark) | Given 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. |
| ProgramBench | 0% | [ProgramBench](https://programbench.com/), retrieved 2026-09-11 | The AI receives a working program and its documentation, then builds a replacement from scratch without the original source code, internet access or decompilation. The score is the percentage of 200 programs that pass every behavioral test. We record each model's best published mini-SWE-agent result, including higher reasoning efforts where available. Partial test-pass rates and almost-solved programs do not count toward this score. Equal scores share a rank here; the official board also uses partial progress to break ties. Higher is better. |
| SWE-Bench Verified | 79.6% | Lab | Real 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. |
| DeepSWE 1.1 | 30% | Lab | Artificial 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. |
| Next.js Evals | 45% | [Next.js Evals](https://nextjs.org/evals) | Vercel'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. |
| MCP Atlas | 69.5% | Lab | Can the AI chain together many tools and steps to complete one bigger task, rather than doing just a single thing? Higher is better. |
| BU Bench | 62% | Lab | Can 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. |
| Humanity's Last Exam (no tools) | 33.2% | Lab | Humanity'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. |
| Humanity's Last Exam (with tools) | 49% | [BenchLM](https://benchlm.ai), retrieved 2026-08-31 | Humanity'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. |
| ARC-AGI-2 | 58.3% | Lab | Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. |
| GPQA Diamond | 89.9% | Lab | Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. |
| OSWorld-Verified | 72.5% | Lab | Can the AI actually operate a computer — clicking, typing, and using real apps — to finish tasks on its own? Higher is better. |
| Finance Agent v2 | 51% | Lab | Tests the AI on real financial-analysis work, like digging through reports and making sound decisions. Higher is better. |
| GDPval-AA | 1676 | Lab | Measures how well the AI does economically valuable knowledge work, judged against human experts. Shown as a rating (like a chess Elo) — higher is better. |
| CharXiv Reasoning | 72.4% | Lab | Can the AI read and reason about complex charts and figures, not just text? Higher is better. |
| MMMU-Pro | 74.5% | Lab | A tougher version of MMMU — college-level questions that mix images, diagrams, and text together. Higher is better. |
| Blueprint-Bench 2 | 6.7% | Lab | Can the AI reason about space and layout — for example, understanding a floor plan or blueprint? Higher is better. |
| MRCR v2 (8-needle) (128k average) | 84.9% | Lab | Tests whether the AI can find specific details buried inside a very long document (around 128k tokens — roughly a long book). Higher is better. |

## Questions and answers

### When was Claude Sonnet 4.6 released?

Claude Sonnet 4.6 was released by Anthropic on Tuesday, Feb 17 2026.

### Who made Claude Sonnet 4.6?

Claude Sonnet 4.6 was built by Anthropic. AI safety company building the Claude family of models. Founded in 2021 by former OpenAI researchers.

### How much does Claude Sonnet 4.6 cost?

Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens through the Anthropic API. Cached input is $0.30 per million tokens. Rates are pay-as-you-go API prices verified against Anthropic's published pricing on August 18, 2026.

### What benchmark scores did Claude Sonnet 4.6 get?

Claude Sonnet 4.6 reports 18 tracked benchmark scores — BullshitBench v2: 91%; ProgramBench: 0%; SWE-Bench Verified: 79.6%; DeepSWE 1.1: 30%; Next.js Evals: 45%; MCP Atlas: 69.5%; BU Bench: 62%; Humanity's Last Exam (no tools): 33.2%; Humanity's Last Exam (with tools): 49%; ARC-AGI-2: 58.3%; GPQA Diamond: 89.9%; OSWorld-Verified: 72.5%; Finance Agent v2: 51%; GDPval-AA: 1676; CharXiv Reasoning: 72.4%; MMMU-Pro: 74.5%; Blueprint-Bench 2: 6.7%; MRCR v2 (8-needle) (128k average): 84.9%. Tracked scores may come from lab reports or independent benchmarks; source details accompany the benchmark data.

### Is Claude Sonnet 4.6 open source?

No. Claude Sonnet 4.6 is a proprietary model. The weights are not published — it is available only through the provider's own API, apps, or partner platforms.

### What came before and after Claude Sonnet 4.6?

Anthropic's previous tracked release was Claude Opus 4.6 on Feb 5 2026, 12 days earlier. It was followed by Claude Opus 4.7 on Apr 16 2026.


---

Canonical page: https://aireleasetracker.com/model/anthropic/claude-sonnet-4.6
Full dataset: https://aireleasetracker.com/llms-full.txt · JSON: https://aireleasetracker.com/models.json
Source: AI Release Tracker (https://aireleasetracker.com). Most benchmark scores come from lab launch material; gathered results identify the leaderboard that published them.