Claude 3 Opus

Claude 3 Opus

Anthropic · Released Mar 4, 2024 Efficient
Intelligence #174 / 556
45.7 Our Score
AA Index #184 / 365
18.0 Artificial Analysis
Input #543 / 557
$15.00 per 1M tokens
Output #547 / 557
$75.00 per 1M tokens
Context
Not reported

Analysis Summary

Claude 3 Opus sits in the Efficient tier on our leaderboard, ranked #174 of 556 published models on overall intelligence. At $15.00 input and $75.00 output per 1M tokens, it is among the most expensive on the market.

Editorial notes

Claude 3 Opus from Anthropic has strong content and instruction-following credentials for its era but is expensive at $15/1M input tokens and superseded by Claude 3.5 and 4.x Opus variants.

Assessed May 14, 2026

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence3.5Technical3.4Value4Content4.5
Intelligence 3.5/10
Technical 3.4/10
Content 4.5/10
Value 4/10

Performance Indices

Source: Artificial Analysis

18 Intelligence Index
19.5 Coding Index

Benchmark Scores

Intelligence

GPQA Diamond 48.9% Graduate-level scientific reasoning
HLE 3.1% Humanity's Last Exam
MMLU Pro 69.6% Multi-task language understanding
MATH 500 64.1% Mathematical problem-solving
AIME 3.3% Competition mathematics
SciCode 23.3% Scientific computing

Technical

LiveCodeBench 27.9% Live coding evaluation

Benchmark data from Artificial Analysis and Hugging Face

How does Claude 3 Opus stack up?

Compare side-by-side with other efficient models.

Compare Models

Model Information

ProviderAnthropic
Release Date March 4, 2024
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $15.00 $0.015000
Output $75.00 $0.075000

Leaderboard Categories