aiintelligence

Claude Opus 4.6

It helps people write computer code and complete long professional tasks.

anthropic’s large language model, able to hold about 1000k tokens of context (roughly 750k words) in one conversation, working across text and image and file->text. You reach it through an API or through tools built on it. Built for professionals who write code and manage long tasks. anthropic describes it as: “Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.” source ↗

Our tested score
89/100 · Humanising AI text
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
88/100 · Book writing
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
80/100 · Health questions
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
82/100 · Legal questions
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
91/100 · Emotional support
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
86/100 · Travel planning
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
85/100 · Translation
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
87/100 · Creative writing
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
83/100 · Research
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
91/100 · CV writing
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
85/100 · Presentations
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
80/100 · Vibe coding
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
83/100 · Job applications
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
86/100 · Social posts
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
88/100 · Flashcards
12 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
84/100 · Coding
18 tasks, marked blind by 3 judges · 16 Aug 2026 · receipts
88/100 · Study notes
12 tasks, marked blind by 3 judges · 14 Aug 2026 · receipts
94/100 · Customer replies
12 tasks, marked blind by 3 judges · 14 Aug 2026 · receipts
98/100 · Maths
12 tasks, marked blind by 3 judges · 14 Aug 2026 · receipts
90/100 · Emails
12 tasks, marked blind by 3 judges · 14 Aug 2026 · receipts
59/100 · Extraction
12 tasks, marked blind by 3 judges · 13 Aug 2026 · receipts
93/100 · Summarising
12 tasks, marked blind by 3 judges · 13 Aug 2026 · receipts
84/100 · Essays
12 tasks, marked blind by 3 judges · 13 Aug 2026 · receipts
82/100 · Spreadsheets
12 tasks, marked blind by 3 judges · 13 Aug 2026 · receipts
83/100 · Best-value API
30 tasks, marked blind by 3 judges · 11 Aug 2026 · receipts
API price (per 1M in/out)
$5 / $25
OpenRouter API17 Aug 2026
Community Elo (text)
1497
LMArena leaderboard (CC-BY-4.0)17 Aug 2026
Battle record
0W – 4L
in our published battles
Forum sentiment (90d)
50%
developer-forum posts: 4 opinions in 49
What people are posting (90 days)
Loudest post this quarter
“Is Opus 5 really lobotomized or it’s just me doing something wrong?”
Battles fought
GLM 5.2 vs Claude Opus 4.6 · Best-value API8–3GLM 5.2 winsKimi K3 vs Claude Opus 4.6 · Best-value API11–3Kimi K3 winsGrok 4.5 vs Claude Opus 4.6 · Best-value API10–5Grok 4.5 winsQwen3.7 Max vs Claude Opus 4.6 · Best-value API9–5Qwen3.7 Max wins

Compare Claude Opus 4.6 against…

GPT-5.6 Sol · essay writingGPT-5.5 · essay writingGPT-5.6 Luna · essay writingGPT-5.6 Terra · essay writingGPT-5.3-Codex · essay writingClaude Sonnet 5 · essay writingGrok 4.5 · essay writingQwen3.7 Max · essay writingGemini 3.1 Pro Preview · essay writingClaude Opus 4.8 · summarising documentsGPT-5.5 · summarising documentsGPT-5.6 Luna · summarising documentsGPT-5.6 Terra · summarising documentsGPT-5.3-Codex · summarising documentsDeepSeek V4 Pro · summarising documentsGPT-5.6 Sol · summarising documentsClaude Sonnet 5 · summarising documentsClaude Fable 5 · summarising documentsClaude Opus 4.8 · everyday maths
Every claim we hold (6)