The Model Index
Up to four models

Claude Opus 4 vs Claude 3 Opus

On the index (GPT-4 = 100), Claude Opus 4 scores 136 and Claude 3 Opus 108. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Claude Opus 4
Presets
Claude Opus 4
136120–151
WeightsClosed
ReleasedMay 2025
Price in / out–
Context–
Core tests taken5 of 9
Claude 3 Opus
10891–124
WeightsClosed
ReleasedMar 2024
Price in / out–
Context–
Core tests taken2 of 9

Claude Opus 4 leads Claude 3 Opus by 28 points, ahead on 2 of 2 shared core tests.

Test by testthird-party results

Claude Opus 4Claude 3 Opus
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)SimpleBenchSimpleBenchMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)MATH (level 5)MATH (level 5)CODINGWeirdMLWeirdMLAGENTSDTBenchDTBenchLMCALMCA
Every result as a table
TestClaude Opus 4Claude 3 Opus
Reasoning & knowledge
GPQA Diamond (Epoch AI)76.3%47.2%
SimpleBench58.8%23.5%
Maths
AIME-style maths (OTIS mock)64.4%4.7%
MATH (level 5)85.0%37.5%
Coding
WeirdML43.7%19.2%
Agents
DTBench81.6%61.6%
LMCA37.4%17.0%
Task length · METR38 sec18 sec

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG