---
title: "Claude 3 Opus Benchmarks - RankedAGI"
description: "Detailed benchmark and metadata record for Claude 3 Opus."
source: "https://rankedagi.com/models/claude-3-opus"
---

# Claude 3 Opus

| Field | Value |
| --- | --- |
| Organization | Anthropic |
| License | Proprietary |
| Version | Latest |
| Released | 2024-03-04 |
| Context window | 200K |
| Knowledge cutoff | 2023-08-01 |
| Input cost per million tokens | $15 |
| Output cost per million tokens | $75 |
| Cached input cost per million tokens | $1.5 |
| Model ID | claude-3-opus-20240229 |
| Last updated | 2025-04-16 22:14:46.146909+00 |

## Benchmarks

| Benchmark | Category | Value | Description | Source |
| --- | --- | --- | --- | --- |
| RankedAGI Coding | coding | 25.6% | RankedAGI Coding Score |  |
| SWEBench Verified | coding | 22.0% | Agentic Coding | https://www.swebench.com/index.html |
| RankedAGI Agentic | Agents | 22.3% | RankedAGI Agentic Score |  |
| ChatArena (LMSYS) | coding | 1236 | ChatArena (LMSYS) Coding ELO Score with Style Control |  |
| LiveBench Coding Score (old) | coding | 38.6% | LiveBench Coding Score old version |  |
| RankedAGI Reasoning | reasoning | 35.3% | RankedAGI Reasoning Score |  |
| GPQA Diamond | reasoning | 50.4% | Generalized Prefix Question Answering Score (Reasoning) PhD Level Reasoning |  |
| Text Arena | general | 1248 | ChatArena (LMSYS) ELO Score | https://arena.ai/leaderboard/text |
| HumanEval | coding | 84.9% | HumanEval coding benchmark |  |
| HumanEval+ | coding | 77.4% | HumanEval+ benchmark |  |
| MMLU Pro | knowledge | 68.5% | Graduate-level visual problem-solving |  |
| MMLU | knowledge | 84.0% | Image Reasoning |  |
| Hughes Hallucination Evaluation | safety | 10.1% | Computed using Vectara's Hallucination Evaluation Model, also known as HHEM. This evaluates how often an LLM introduces hallucinations when summarizing a document. | https://github.com/vectara/hallucination-leaderboard |
| AidanBench | general | 908 | AidanBench Score |  |
| LiveBench Average | general | 56.2% | LiveBench Average Score old version |  |
| LiveBench Data Analysis | general | 54.3% | LiveBench Data Analysis Score | https://livebench.ai/ |
| LiveBench Language | general | 50.4% | LiveBench Language Score | https://livebench.ai/ |
| Artificial Analysis Quality Index | general | 70 | Artificial Analysis Quality Index (third-party composite, deprecated) |  |
| RankedAGI Math | math | 45.0% | RankedAGI Math Score |  |
| RankedAGI Overall | general | 35.7% | Overall RankedAGI score |  |