#1
Claude Opus 4.7
claude-opus-4-7
0.0
Helpfulness
Instruction Following
Comprehension
Empathy
Creative Writing
Helpfulness
0.0
Instruction Following
0.0
Comprehension
0.0
Empathy
0.0
Creative Writing
0.0
Speed
Avg 65 tok/s
Release Date
April 16th, 2026
Lab
Anthropic
Type
Proprietary
Context Size
200K
Max Output Tokens
8.2K
Cost per 1 million tokens
$5.00 / $25.00
Model Inputs*
Text, Images
Model Outputs*
Text
Tool Calling*
Enabled
Overall Assistant Score
An average score combining the 5 main categories.
95.30 pts
Rank #1
100th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
Claude Opus 4.7 is Anthropic's most capable model yet, designed to handle long-running tasks with exceptional rigor. It achieves the #1 spot across all major benchmarks, including comprehension, instruction following, and helpfulness. With improved ability to verify its own outputs, it requires less supervision for complex workflows, though its massive size results in slower generation speeds.

Intelligence

Overall Score; Higher is better

Claude Opus…
Claude Opus…
Gemini 3.1 …
Claude Opus…
Claude Sonn…
GPT-5.4
Gemini 3 Pro
Claude Sonn…
GPT 5.1
o3

Speed

Output Tokens per Second; Higher is better

Grok 4
GLM 4.6
Claude Sonn…
Grok 3
GLM 4.7
Claude Opus…
Kimi K2.5
o1
Grok 4.1 Fa…
Gemini 2.5 …

Price

USD per 1M Tokens; Lower is better

GPT 4o
Claude Sonn…
Claude Sonn…
Grok 3
Grok 4
Claude Opus…
Claude Opus…
Claude Opus…
ChatGPT 4o
Claude Opus…

Anthropic Models

Overall Score; Same provider comparison

Claude Opus…
Claude Opus…
Claude Opus…
Claude Sonn…
Claude Sonn…
Claude Opus…
Claude Haik…

Claude Opus Family

Overall Score; Same model family comparison

Claude Opus…
Claude Opus…
Claude Opus…
Claude Opus…

Closest Rivals

Overall Score; Nearest by overall rank

Claude Opus…
Claude Opus…
Gemini 3.1 …
Claude Opus…
Claude Sonn…
GPT-5.4
Gemini 3 Pro
Claude Sonn…
GPT 5.1
o3