Claude Opus 4.8
Claude Opus 4.8 is a closed AI model from Anthropic with an index score of 170 (GPT-4 = 100), rank 26 of 217.
170154–186Index score#26 of 217 models
$5.0/ $25Price per million tokensinput / output · via OpenRouter
1MContext windowtokens it reads at once
28 May 2026ReleasedReplaced by Claude Opus 5
Where it sitson the frontier
GPT-5.5 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 others sayrank on 12 leaderboards
The Model Indexthird-party tests, our method#26of 217 · 170
LMArena · Instruction followingfollowing detailed instructions#11of 362 · 1492LMArena · Long promptslong, complex requests#11of 340 · 1503LMArena · Codingcoding questions in chat#14of 357 · 1534LMArena · Creative writingcreative writing#18of 360 · 1470LMArena · Textoverall chat quality, judged by people#24of 362 · 1482LMArena · Mathsmaths questions in chat#23of 346 · 1492Epoch Capabilities Indexoverall capability from many benchmarks#22of 231 · 159.9LMArena · Visionunderstanding images#15of 145 · 1286LMArena · Documentsworking with long documents#11of 40 · 1475LMArena · WebDevbuilding web apps and front ends#47of 133 · 1555LMArena · Searchanswering with web search#19of 41 · 1202Best 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 May 2026
Announcementanthropic.com ↗
Release entryClaude Opus 4.8
Scored asClaude Opus 4.8
Output speed–
Hugging Faceclosed weights