Claude Opus 5.5
Claude Opus 5.5 is a closed AI model from Anthropic with an index score of 195 (GPT-4 = 100), rank 5 of 217.
195178–211Index score#5 of 217 models
$4.0/ $20Price per million tokensinput / output · via OpenRouter
1MContext windowtokens it reads at once
22 Sep 2026Released2 months ago
Where it sitson the frontier
Among the first models to reach this score.
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 says2 of 9 also run by third parties
| Test | Anthropic says | Third parties |
|---|---|---|
| Terminal-Bench 4.0Claude Code harness, 5 tries per task. Anthropic gives a margin of ±2.6 points. | 66.4% | 65.1%Vals AI |
| Terminal-Bench Science 0.1Claude Code harness, 3 tries per task. Anthropic gives a margin of ±3.5–5 points. | 58.7% | 47.1%Vals AI |
| FrontierCode v1.1 (Main) | 54.4% | not run yet |
| CursorBench 4.0 | 57.8% | not run yet |
| GDPval-AA v2.1 | 1846 Elo | not run yet |
| AutomationBench | 40.0% | not run yet |
| Humanity's Last Examwith tools | 67.7% | not run yet |
| OSWorld 2.1partial credit | 81.8% | not run yet |
| Chartographywith tools | 89.0% | not run yet |
From Anthropic’s launch post, Introducing Claude Opus 5.5, copied from the table in the post. Shown, never scored; settings can differ from the third-party run.
What others sayrank on 12 leaderboards
The Model Indexthird-party tests, our method#5of 217 · 195
LMArena · Creative writingcreative writing#2of 360 · 1517LMArena · Instruction followingfollowing detailed instructions#3of 362 · 1518LMArena · Textoverall chat quality, judged by people#4of 362 · 1507LMArena · Long promptslong, complex requests#5of 340 · 1520LMArena · WebDevbuilding web apps and front ends#2of 133 · 1816LMArena · Codingcoding questions in chat#6of 357 · 1547LMArena · Mathsmaths questions in chat#7of 346 · 1514Epoch Capabilities Indexoverall capability from many benchmarks#5of 231 · 168.7LMArena · Visionunderstanding images#5of 145 · 1295LiveBench · Overalloverall, on regularly refreshed questions#6of 38 · 83.4LMArena · Searchanswering with web search#14of 41 · 1213Best attop three among current models
1stTerminal-Bench 4.0Vals AI · third-party2ndcreative writingLMArena · Creative writing2ndbuilding web apps and front endsLMArena · WebDev2ndunderstanding imagesLMArena · Vision2ndagentic questionsLiveBench · Agentic2nddesign questionsLiveBench · Design2ndARC-AGI-2ARC Prize · third-party3rdcoding questions in chatLMArena · Coding3rdmaths questions in chatLMArena · Maths3rdfollowing detailed instructionsLMArena · Instruction following
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
Released22 Sep 2026
Announcementanthropic.com ↗
Release entryClaude Opus 5.5
Scored asClaude Opus 5.5
Output speed–
Hugging Faceclosed weights