Claude Sonnet 5.5
Claude Sonnet 5.5 is a closed AI model from Anthropic with an index score of 187 (GPT-4 = 100), rank 12 of 217.
187171–203Index score#12 of 217 models
$2.0/ $10Price per million tokensinput / output · via OpenRouter
1MContext windowtokens it reads at once
28 Sep 2026Released2 months ago
Where it sitson the frontier
Claude Fable 5.1 reached this score 1 month earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsevidence
Professional workevidence
Novel problemsevidence
Long tasksno evidence yet
Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.
What the lab says1 of 8 also run by third parties
| Test | Anthropic says | Third parties |
|---|---|---|
| Terminal-Bench 4.0 | 70.6% | 64.1%Vals AI |
| FrontierCode 1.1 (Main)max effort | 46.2% | not run yet |
| CursorBench 4.0 | 55.5% | not run yet |
| GDPval-AA v2.1 | 1844 Elo | not run yet |
| AA-Briefcase v1.1 | 1811 Elo | not run yet |
| Humanity's Last Examwith tools | 64.5% | not run yet |
| OSWorld 2.1partial credit | 80.1% | not run yet |
| Chartographyno tools | 61.6% | not run yet |
From Anthropic’s launch post, Introducing Claude Sonnet 5.5, copied from the table in the post. Shown, never scored; settings can differ from the third-party run.
What others sayrank on 11 leaderboards
The Model Indexthird-party tests, our method#12of 217 · 187
LMArena · WebDevbuilding web apps and front ends#3of 133 · 1772Epoch Capabilities Indexoverall capability from many benchmarks#9of 231 · 166.6LMArena · Instruction followingfollowing detailed instructions#19of 362 · 1482LMArena · Creative writingcreative writing#24of 360 · 1464LMArena · Long promptslong, complex requests#25of 340 · 1491LMArena · Mathsmaths questions in chat#29of 346 · 1486LMArena · Codingcoding questions in chat#40of 357 · 1517LMArena · Textoverall chat quality, judged by people#41of 362 · 1473LMArena · Visionunderstanding images#36of 145 · 1263LiveBench · Overalloverall, on regularly refreshed questions#12of 38 · 77Best attop three among current models
Where to use itprices checked 18 Nov 2026
API providers 5 · per 1M tokens, in / out
Host prices from OpenRouter; going direct can differ.
Facts and sources
Released28 Sep 2026
Announcementanthropic.com ↗
Release entryClaude Sonnet 5.5
Scored asClaude Sonnet 5.5
Output speed–
Hugging Faceclosed weights