Serenities AI™
Anthropic

Claude 3 Opus — Benchmark Scores, Pricing & Performance Analysis

FLAGSHIPAnthropic
Chatbot Arena ELO
1240
Output Speed
25 tok/s
Input Cost
$15.0/1M
Output Cost
$75.0/1M
Context Window
200K

Claude 3 Opus is an AI model by Anthropic. View detailed benchmark scores, pricing data, and performance metrics on Serenities AI Models.

General Benchmarks

Chatbot Arena ELO
124059th of 74

Human preference ELO from blind head-to-head votes

LMSYS / HuggingFace
MMLU-Pro
68.0%46th of 66

Massive Multitask Language Understanding professional benchmark

HuggingFace Leaderboard
IFEval
82.0%24th of 25

Strict instruction following accuracy on verifiable constraints

Google Research
SimpleQA
29.0%7th of 14

Factual accuracy on short, verifiable questions

OpenAI
TruthfulQA
81.0%7th of 13

Resistance to generating false but plausible answers

Papers
MT-Bench
8.88th of 13

Multi-turn conversation quality on 80 curated dialogues

LMSYS

Coding Benchmarks

HumanEval+
78.0%48th of 66

Code generation correctness with extended tests

Papers
SWE-bench Verified
22.0%57th of 67

Real-world software engineering task resolution

swebench.com
LiveCodeBench
32.0%52nd of 66

Live competitive programming benchmark

livecodebench.github.io

Math Benchmarks

GSM8K
88.0%47th of 66

Grade school math word problems

Papers
MATH
68.0%52nd of 66

Competition mathematics problem solving

Papers

Reasoning Benchmarks

ARC-AGI
8.0%60th of 66

Abstraction and Reasoning Corpus for general intelligence

arcprize.org
GPQA Diamond
59.4%103rd of 140

Graduate-level science Q&A by domain experts

Papers
Winogrande
90.5%7th of 14

Commonsense reasoning via pronoun resolution

Papers
BBH
86.8%9th of 13

Big-Bench Hard — 23 challenging multi-step reasoning tasks

Google Research

Speed Benchmarks

Time to First Token
800 ms71st of 92

Latency before first token arrives

Aggregated
Output Speed
25 tok/s91st of 94

Tokens generated per second

Aggregated

Cost Benchmarks

Output Cost
$75.0403rd of 413

Cost per 1M output tokens

OpenRouter API
Input Cost
$15.0401st of 413

Cost per 1M input tokens

OpenRouter API

Context Benchmarks

Context Length
200K189th of 451

Maximum context window size

OpenRouter API

Available from 1 provider

The same model costs different amounts depending on who serves it.

ProviderInput / 1MOutput / 1MCached inContextYour key
DigitalOcean$15$75$1.5200K—

Claude 3 Opus — Benchmark Scores Overview

Scores normalized to percentage scale for visual comparison. ELO scores mapped to 0-100 range (1100-1500).

Compare Claude 3 Opus With

Claude 3 Opus vs Gemini 2.5 ProClaude 3 Opus vs o3Claude 3 Opus vs Claude Sonnet 4.6Claude 3 Opus vs Gemini 3.1 ProClaude 3 Opus vs Claude Sonnet 4.5Claude 3 Opus vs Claude Opus 4.6Claude 3 Opus vs GPT-5.1Claude 3 Opus vs Claude Opus 4.5Claude 3 Opus vs GPT-5Claude 3 Opus vs GPT-5.2Claude 3 Opus vs Mistral Large 25.12Claude 3 Opus vs o1

Claude 3 Opus — Frequently Asked Questions

How intelligent is Claude 3 Opus?

Claude 3 Opus scores 1240 on the Chatbot Arena ELO rating, making it an entry-level AI model. This score is based on blind head-to-head human preference voting.

How much does Claude 3 Opus cost?

Claude 3 Opus costs $15.0 per 1M input tokens and $75.0 per 1M output tokens. This places it in the premium pricing tier.

How fast is Claude 3 Opus?

Claude 3 Opus generates output at 25 tokens per second, which is slower, prioritizing quality over speed compared to other models. The time to first token is 800 ms.

How good is Claude 3 Opus at coding?

Claude 3 Opus achieves 22.0% on SWE-bench Verified, demonstrating basic real-world software engineering capability. This benchmark tests the model's ability to resolve actual GitHub issues.

How good is Claude 3 Opus at math and reasoning?

Claude 3 Opus scores 68.0% on the MATH benchmark (competition-level mathematics). It also achieves 59.4% on GPQA Diamond, a graduate-level science reasoning benchmark.

What is the context window of Claude 3 Opus?

Claude 3 Opus has a context window of 200K tokens. This determines how much text, conversation history, and code the model can process in a single request.

Who created Claude 3 Opus?

Claude 3 Opus was created by Anthropic. It is classified as a flagship model in our catalogue.

Is Claude 3 Opus open source?

No, Claude 3 Opus is a proprietary model. It is available through Anthropic's API and compatible providers.

Back to AI Models