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

# Claude 4 Sonnet

| 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 | 2026-05-04T03:43:08.354Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 55.8% | RankedAGI Coding Score |  |
| SWEBench Verified | coding | 72.7% | Agentic Coding | https://www.swebench.com/index.html |
| RankedAGI Agentic | Agents | 49.1% | RankedAGI Agentic Score |  |
| SvelteBench | coding | 90.0% | SvelteBench - Benchmark for Svelte | https://khromov.github.io/svelte-bench/benchmark-results-merged.html |
| LiveCodeBench v6 | coding | 48.4% | LiveCodeBench v6 - Evaluation of Large Language Models for Code |  |
| LiveBench Coding 25.5 | coding | 78.3% | LiveBench Coding Score 2025-05-30 |  |
| ChatArena (LMSYS) | coding | 1432 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| CyberGym | safety | 22.6% |  |  |
| Aider Polyglot | coding | 56.4% | Aider Polyglot Code Completion Benchmark |  |
| RankedAGI Reasoning | reasoning | 47.6% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 7.7% | Multidisciplinary Reasoning (no tools) |  |
| GPQA Diamond | reasoning | 83.8% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| LiveBench Reasoning 25.5 | reasoning | 54.9% | LiveBench Reasoning Score 2025-05-30 |  |
| Text Arena | general | 1390 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| AIME 2025 | math | 85.0% | AIME 2025 Competition Math |  |
| LiveBench Math Score | math | 76.4% | LiveBench Math Score 25-05 |  |
| MMMU | imaging | 74.4% | Multimodal Understanding College-level visual problem-solving |  |
| LiveBench IF 25.5 | instruction-following | 77.3% | LiveBench Instruction Following Score 2025-05-30 |  |
| LiveBench Average 25.5 | general | 62.4% | LiveBench Average Score 2025-05-30 |  |
| LiveBench Coding 25.4 | coding | 78.3% | LiveBench Coding Score 2025-04 | https://livebench.ai/ |
| LiveBench Agentic Coding 25.5 | coding | 25.0% | LiveBench Agentic Coding Score 2025-05-30 | https://livebench.ai/ |
| RankedAGI Math | math | 60.6% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 51.5% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 1134 | Office Tasks (Artificial Analysis) |  |
| SvelteBench old | coding | 88.9% | SvelteBench - Benchmark for Svelte (Old v1) | https://khromov.github.io/svelte-bench/v1/v1-benchmark-results-merged.html |
| Code DesignArena | Design | 1206 |  | https://www.designarena.ai/leaderboard/code |
| Toolathlon | Agents | 29.9% | 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-4 |