---
title: "Claude Sonnet 4.6 Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Claude Sonnet 4.6."
source: "https://rankedagi.com/models/claude-sonnet-4-6"
---

# Claude Sonnet 4.6

| Field | Value |
| --- | --- |
| Organization | Anthropic |
| License | Proprietary |
| Type | Thinking |
| Version | Latest |
| Released | 2026-02-17 |
| Input cost per million tokens | $3 |
| Output cost per million tokens | $15 |
| Cached input cost per million tokens | $0.3 |
| Last updated | 2026-05-04T03:43:08.354Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 80.8% | RankedAGI Coding Score |  |
| SWEBench Verified | coding | 79.6% | Agentic Coding | https://www.swebench.com/index.html |
| Terminal-Bench 2.0 | coding | 59.1% | Agentic Terminal Coding | https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| RankedAGI Agentic | Agents | 66.9% | RankedAGI Agentic Score |  |
| BrowseComp | Agents | 74.7% | A benchmark for browsing agents | https://openai.com/index/browsecomp/ |
| Code Arena | coding | 1525 | Code Arena Elo Score | https://arena.ai/leaderboard/code |
| Livebench Coding 26.1 | coding | 87.0% | Livebench Coding 26.01.08 | https://livebench.ai/#/?Coding=a&sort=Coding+Average&variants=true&highunseenbias=true |
| LiveBench Agentic Coding 26.1 | coding | 63.3% |  | https://livebench.ai/#/?Agentic+Coding=a&sort=Agentic+Coding+Average&variants=true&highunseenbias=true |
| OSWorld-Verified | Agents | 71.5% |  |  |
| SvelteBench | coding | 100.0% | SvelteBench - Benchmark for Svelte | https://khromov.github.io/svelte-bench/benchmark-results-merged.html |
| CyberGym | safety | 65.2% |  |  |
| RankedAGI Reasoning | reasoning | 74.2% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 33.2% | Multidisciplinary Reasoning (no tools) |  |
| Humanity's Last Exam w/ Tools | reasoning | 49.0% | Multidisciplinary Reasoning (with tools) |  |
| GPQA Diamond | reasoning | 89.9% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1463 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| Vending Bench 2 | Agents | $7,204.14 | Benchmark for measuring AI model performance on running a business over long time horizons. Models are tasked with running a simulated vending machine business over a year and scored on their bank account balance at the end. | https://andonlabs.com/evals/vending-bench-2 |
| NYT Connections Extended | reasoning | 85.7% | NYT Connections Extended Version | https://github.com/lechmazur/nyt-connections/ |
| RankedAGI Math | math | 73.0% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 67.0% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 1675 | Office Tasks (Artificial Analysis) |  |
| Code DesignArena | Design | 1336 |  | https://www.designarena.ai/leaderboard/code |
| Toolathlon | Agents | 44.8% | Benchmark to assess language agents' general tool use in realistic environments. | https://toolathlon.xyz/introduction |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://www.anthropic.com/news/claude-sonnet-4-6 |