Anthropic
Claude Opus 5.5
Claude Opus 5.5 is the newest Opus model from Anthropic, released in September 2026. It ranks number 1 of 79 with a score of 10.0 out of 10, among the very best available. Its best areas are writing and editing (9.8/10) and creative writing (9.8/10); business and finance (9.4/10) is the weakest of the nine tasks we track. In blind votes against Gemini 4 Argon, the model people prefer most, it was picked about 48 times in 100. It needs a paid plan, from $20 a month. For developers it costs more than about 88% of the models we rank.
Rank 1 of 79
What it's good for
Emails, reports, rewriting and proofreading
Stories, poems, speeches and ideas
Writing, fixing and explaining code
General health information (not medical advice)
Doing exactly what you ask, in the format you ask
Explaining and researching science and social topics
Working in languages other than English
Calculations, puzzles and step-by-step problems
Plans, analysis, spreadsheets and money questions
Out of 10, compared with the best model at each task
Related models
Anthropic
Claude Fable 5.1
9.5/10 Best available
Claude Fable 5.1 is the newest Fable model from Anthropic, released in September 2026. It ranks number 4 of 79 with a score of 9.5 out of 10, among the very best available. Its best areas are health questions (10.0/10) and maths (9.7/10); creative writing (9.1/10) is the weakest of the nine tasks we track. In blind votes against Gemini 4 Argon, the model people prefer most, it was picked about 47 times in 100. It needs a paid plan, from $100 a month. For developers it is among the priciest models we rank.
From $100 a month
Anthropic
Claude Sonnet 5.5
9.1/10 Very strong
Claude Sonnet 5.5 is the newest Sonnet model from Anthropic, released in September 2026. It ranks number 6 of 79 with a score of 9.1 out of 10, a very strong result. Its best areas are coding (9.0/10) and business and finance (8.8/10); creative writing (8.3/10) is the weakest of the nine tasks we track. In blind votes against Gemini 4 Argon, the model people prefer most, it was picked about 43 times in 100. You can use it free in Anthropic's own app. For developers it costs more than about 75% of the models we rank.
Free plan
Anthropic
Claude Fable 5
8.9/10 Very strong
Claude Fable 5 is an earlier Anthropic model from June 2026; the newer Claude Fable 5.1 is also in our ranking. It ranks number 7 of 79 with a score of 8.9 out of 10, a very strong result. Its best areas are coding (9.9/10) and science and research (9.7/10); other languages (9.4/10) is the weakest of the nine tasks we track. In blind votes against Gemini 4 Argon, the model people prefer most, it was picked about 48 times in 100. It needs a paid plan, from $100 a month. For developers it is among the priciest models we rank.
From $100 a month