---
title: "Claude Opus 4.5 Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Claude Opus 4.5."
source: "https://rankedagi.com/models/claude-opus-4-5"
---

# Claude Opus 4.5

| Field | Value |
| --- | --- |
| Organization | Anthropic |
| License | Proprietary |
| Type | Thinking |
| Version | Latest |
| Released | 2025-11-24 |
| Last updated | 2026-05-04T03:43:08.354Z |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 77.2% | RankedAGI Coding Score |  |
| SWEBench Verified | coding | 80.9% | Agentic Coding | https://www.swebench.com/index.html |
| Terminal-Bench 2.0 | coding | 59.8% | Agentic Terminal Coding | https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| RankedAGI Agentic | Agents | 59.9% | RankedAGI Agentic Score |  |
| BrowseComp | Agents | 72.9% | A benchmark for browsing agents | https://openai.com/index/browsecomp/ |
| Code Arena | coding | 1491 | Code Arena Elo Score | https://arena.ai/leaderboard/code |
| Livebench Coding 26.1 | coding | 79.7% | 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 | 66.3% |  |  |
| SvelteBench | coding | 100.0% | SvelteBench - Benchmark for Svelte | https://khromov.github.io/svelte-bench/benchmark-results-merged.html |
| CyberGym | safety | 50.6% |  |  |
| Aider Polyglot | coding | 89.4% | Aider Polyglot Code Completion Benchmark |  |
| RankedAGI Reasoning | reasoning | 64.9% | RankedAGI Reasoning Score |  |
| Humanity's Last Exam | reasoning | 30.8% | Multidisciplinary Reasoning (no tools) |  |
| Humanity's Last Exam w/ Tools | reasoning | 43.4% | Multidisciplinary Reasoning (with tools) |  |
| GPQA Diamond | reasoning | 87.0% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1469 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| Vending Bench 2 | Agents | $4,967.06 | 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 |
| MMMU | imaging | 80.7% | Multimodal Understanding College-level visual problem-solving |  |
| MMMU-Pro | imaging | 70.6% | Multimodal Understanding |  |
| MMMU Pro w/Tools | imaging | 73.9% |  |  |
| RankedAGI Math | math | 73.5% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 62.9% | Overall RankedAGI score |  |
| ARC AGI 2 | reasoning | 37.6% | Abstract Reasoning Puzzles (Public) |  |
| 𝜏²-Bench Telecom | Agents | 95.2% | Agentic Tool Use |  |
| 𝜏²-Bench Retail | Agents | 88.9% | Agentic Tool Use |  |
| GDPval-AA Elo | Agents | 1451 | Office Tasks (Artificial Analysis) |  |
| MCP Atlas | Agents | 62.3% | Scaled Tool Use |  |
| Finance Agent | Agents | 55.9% | Agentic Financial Analysis |  |
| MMMLU | Uncategorized | 90.8% | Multilingual Q&A |  |
| Code DesignArena | Design | 1305 |  | https://www.designarena.ai/leaderboard/code |
| Toolathlon | Agents | 43.5% | 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-opus-4-5 |