---
title: "Claude Opus 4.7 Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Claude Opus 4.7."
source: "https://rankedagi.com/models/claude-opus-4-7"
---

# Claude Opus 4.7

| Field | Value |
| --- | --- |
| Organization | Anthropic |
| License | Proprietary |
| Type | Thinking |
| Version | Latest |
| Released | 2026-04-16 |
| Input cost per million tokens | $5 |
| Output cost per million tokens | $25 |
| Model ID | claude-opus-4-7 |
| Last updated | 2026-05-28T21:32:30.135Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 86.5% | RankedAGI Coding Score |  |
| SWEBench Pro | coding | 64.3% | Diverse Agentic Coding |  |
| SWEBench Multilingual | coding | 79.5% |  |  |
| SWEBench Verified | coding | 87.6% | Agentic Coding | https://www.swebench.com/index.html |
| Terminal-Bench 2.0 | coding | 69.4% | Agentic Terminal Coding | https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| Terminal-Bench 2.1 | coding | 69.7% | Agentic Terminal Coding | https://www.tbench.ai/leaderboard/terminal-bench/2.1 |
| RankedAGI Agentic | Agents | 75.8% | RankedAGI Agentic Score |  |
| BrowseComp | Agents | 79.3% | A benchmark for browsing agents | https://openai.com/index/browsecomp/ |
| Code Arena | coding | 1571 | Code Arena Elo Score | https://arena.ai/leaderboard/code |
| Livebench Coding 26.1 | coding | 83.1% | Livebench Coding 26.01.08 | https://livebench.ai/#/?Coding=a&sort=Coding+Average&variants=true&highunseenbias=true |
| DeepSWE | coding | 54.0% | Measuring frontier coding agents on original, long-horizon engineering tasks | https://deepswe.datacurve.ai/ |
| LiveBench Agentic Coding 26.1 | coding | 61.7% |  | https://livebench.ai/#/?Agentic+Coding=a&sort=Agentic+Coding+Average&variants=true&highunseenbias=true |
| OSWorld-Verified | Agents | 78.0% |  |  |
| SvelteBench | coding | 100.0% | SvelteBench - Benchmark for Svelte | https://khromov.github.io/svelte-bench/benchmark-results-merged.html |
| CyberGym | safety | 73.1% |  |  |
| RankedAGI Reasoning | reasoning | 71.0% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 46.9% | Multidisciplinary Reasoning (no tools) |  |
| Humanity's Last Exam w/ Tools | reasoning | 54.7% | Multidisciplinary Reasoning (with tools) |  |
| GPQA Diamond | reasoning | 94.2% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1505 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| Vending Bench 2 | Agents | $10,936.76 | 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 | 41.0% | NYT Connections Extended Version | https://github.com/lechmazur/nyt-connections/ |
| RankedAGI Math | math | 71.8% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 69.5% | Overall RankedAGI score |  |
| ARC AGI 2 | reasoning | 75.8% | Abstract Reasoning Puzzles (Public) |  |
| GDPval-AA Elo | Agents | 1753 | Office Tasks (Artificial Analysis) |  |
| MCP Atlas | Agents | 78.3% | Scaled Tool Use |  |
| Finance Agent | Agents | 64.4% | Agentic Financial Analysis |  |
| MMMLU | Uncategorized | 91.5% | Multilingual Q&A |  |
| CharXiv Reasoning | Multimodal | 82.1% | Figure Understanding |  |
| CharXiv Reasoning w/ Tools | Multimodal | 91.0% | Figure Understanding |  |
| Code DesignArena | Design | 1349 |  | https://www.designarena.ai/leaderboard/code |
| Toolathlon | Agents | 52.8% | Benchmark to assess language agents' general tool use in realistic environments. | https://toolathlon.xyz/introduction |
| Cursor Bench 3.1 | coding | 64.8% | Benchmark to evaluate agents on ambiguous, multi-file tasks from real Cursor sessions. | https://cursor.com/evals |

## Model Links

| Title | URL |
| --- | --- |
| Release | https://www.anthropic.com/news/claude-opus-4-7 |