#2
Claude Opus 5.5
claude-opus-5-5
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 54 tok/s
Release Date
September 22nd, 2026
Lab
Anthropic
Type
Proprietary
Context Size
1M
Max Output Tokens
128K
Cost per 1 million tokens
$4.00 / $20.00
Model Inputs*
Text, Images
Model Outputs*
Text
Tool Calling*
Enabled
Overall Assistant Score
An average score combining the 5 main categories.
96.50 pts
Rank #2
99th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
Claude Opus 5.5 is Anthropic's September 22nd, 2026 Opus refresh — Fable-level everyday help at $4/$20. Our tests score helpfulness 97.0, instruction following 98.0, and comprehension 98.0, just behind Claude Fable 5.1. Empathy is 95.5: warm and careful, short of Fable's 97.0. Creative writing is 94.0: clearer than Opus 5's 78.0, still less literary than Fable's 97.0. Speed is 54.0 with thinking always on. Best when you want Fable-like follow-through without Fable's bill.

Overall Score vs Price

Price axis is logarithmic (USD per 1M input tokens) · Higher score and lower price is better

Ringed point is this model

Anthropic
Baidu
Bytedance
DeepSeek
Google
Meta
Minimax
Mistral
Moonshot
OpenAI
Qwen
SpaceX AI
Tencent
Xiaomi
Zhipu AI

Intelligence

Overall Score · Higher is better

Speed

Output tokens per second · Higher is better

Price

USD per 1M input tokens · Lower is better

Anthropic Models

Overall Score · Same provider

Claude Opus Family

Overall Score · Same model family

Closest Rivals

Overall Score · Nearest by overall rank