---
title: "Claude 3.7 Sonnet Thinking Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Claude 3.7 Sonnet Thinking."
source: "https://rankedagi.com/models/claude-3.7-sonnet-thinking"
---

# Claude 3.7 Sonnet Thinking

| Field | Value |
| --- | --- |
| Organization | Anthropic |
| License | Proprietary |
| Type | Thinking |
| Version | Latest |
| Released | 2025-02-24 |
| Context window | 200K |
| Knowledge cutoff | 2024-10-01 |
| Input cost per million tokens | $3 |
| Output cost per million tokens | $15 |
| Model ID | claude-3-7-sonnet-20250219 |
| Last updated | 2026-04-20T06:31:08.290Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 47.4% | RankedAGI Coding Score |  |
| RankedAGI Agentic | Agents | 39.2% | RankedAGI Agentic Score |  |
| LiveBench Coding 25.5 | coding | 73.2% | LiveBench Coding Score 2025-05-30 |  |
| ChatArena (LMSYS) | coding | 1333 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| Aider Polyglot | coding | 64.9% | Aider Polyglot Code Completion Benchmark |  |
| LiveBench Coding Score (old) | coding | 71.5% | LiveBench Coding Score old version |  |
| RankedAGI Reasoning | reasoning | 44.9% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 8.9% | Multidisciplinary Reasoning (no tools) |  |
| GPQA Diamond | reasoning | 78.2% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| LiveBench Reasoning 25.5 | reasoning | 76.2% | LiveBench Reasoning Score 2025-05-30 |  |
| Text Arena | general | 1363 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| AIME 2025 | math | 49.5% | AIME 2025 Competition Math |  |
| AIME 2024 | math | 80.0% | AIME 2024 Competition Math |  |
| LiveBench Math Score | math | 79.0% | LiveBench Math Score 25-05 |  |
| NYT Connections Extended | reasoning | 33.6% | NYT Connections Extended Version | https://github.com/lechmazur/nyt-connections/ |
| MMMU | imaging | 75.0% | Multimodal Understanding College-level visual problem-solving |  |
| LiveBench IF 25.5 | instruction-following | 81.3% | LiveBench Instruction Following Score 2025-05-30 |  |
| LiveBench Average 25.5 | general | 66.9% | LiveBench Average Score 2025-05-30 |  |
| LiveBench Average | general | 74.3% | LiveBench Average Score old version |  |
| Instruction Following Evaluation | instruction-following | 93.2% | Instruction Following Evaluation |  |
| LiveBench Coding 25.4 | coding | 44.7% | LiveBench Coding Score 2025-04 | https://livebench.ai/ |
| LiveBench Data Analysis | general | 72.8% | LiveBench Data Analysis Score | https://livebench.ai/ |
| LiveBench Language | general | 61.0% | LiveBench Language Score | https://livebench.ai/ |
| LiveBench Agentic Coding 25.5 | coding | 25.0% | LiveBench Agentic Coding Score 2025-05-30 | https://livebench.ai/ |
| RankedAGI Math | math | 56.3% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 46.7% | Overall RankedAGI score |  |
| GDPval-AA Elo | Agents | 1054 | Office Tasks (Artificial Analysis) |  |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://www.anthropic.com/news/claude-3-7-sonnet |