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

# Claude 4 Sonnet Thinking

| Field | Value |
| --- | --- |
| Organization | Anthropic |
| License | Proprietary |
| Version | Latest |
| Released | 2025-05-22 |
| Context window | 1M |
| Knowledge cutoff | 2025-03-01 |
| Input cost per million tokens | $3 |
| Output cost per million tokens | $15 |
| Cached input cost per million tokens | $0.3 |
| Model ID | claude-sonnet-4-20250514 |
| Last updated | 2026-04-23T16:22:43.046Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 55.5% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 46.7% | RankedAGI Agentic Score |  |
| LiveCodeBench v6 | coding | 57.0% | LiveCodeBench v6 - Evaluation of Large Language Models for Code |  |
| LiveBench Coding 25.5 | coding | 73.6% | LiveBench Coding Score 2025-05-30 |  |
| Aider Polyglot | coding | 61.3% | Aider Polyglot Code Completion Benchmark |  |
| RankedAGI Reasoning | reasoning | 59.4% | RankedAGI Reasoning Score |  |
| LiveBench Reasoning 25.5 | reasoning | 95.3% | LiveBench Reasoning Score 2025-05-30 |  |
| LiveBench Math Score | math | 85.3% | LiveBench Math Score 25-05 |  |
| LiveBench IF 25.5 | instruction-following | 80.4% | LiveBench Instruction Following Score 2025-05-30 |  |
| LiveBench Average 25.5 | general | 72.9% | LiveBench Average Score 2025-05-30 |  |
| LiveBench Coding 25.4 | coding | 73.6% | LiveBench Coding Score 2025-04 | https://livebench.ai/ |
| LiveBench Reasoning 25.4 | reasoning | 95.3% | LiveBench Reasoning Score 2025-04 | https://livebench.ai/ |
| LiveBench Agentic Coding 25.5 | coding | 30.0% | LiveBench Agentic Coding Score 2025-05-30 | https://livebench.ai/ |
| RankedAGI Math | math | 63.5% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 53.4% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 1136 | Office Tasks (Artificial Analysis) |  |
| Code DesignArena | Design | 1201 |  | https://www.designarena.ai/leaderboard/code |

## Model Links

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