GPT-5.5
GPT-5.5 is a closed AI model from OpenAI with an index score of 172 (GPT-4 = 100), rank 22 of 217.
172156–188Index score#22 of 217 modelsPro mode: 177 · $30 / $180
$5.0/ $30Price per million tokensinput / output · via OpenRouter
1.05MContext windowtokens it reads at once
23 Apr 2026ReleasedReplaced by GPT-5.6 Sol
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 others sayrank on 12 leaderboards
The Model Indexthird-party tests, our method#22of 217 · 172
LMArena · Mathsmaths questions in chat#16of 346 · 1500LMArena · Instruction followingfollowing detailed instructions#25of 362 · 1477LMArena · Textoverall chat quality, judged by people#26of 362 · 1481LMArena · Long promptslong, complex requests#29of 340 · 1487LMArena · Creative writingcreative writing#32of 360 · 1451Epoch Capabilities Indexoverall capability from many benchmarks#21of 231 · 160.2LMArena · Searchanswering with web search#4of 41 · 1246LMArena · Codingcoding questions in chat#37of 357 · 1518LMArena · Visionunderstanding images#17of 145 · 1285LMArena · Documentsworking with long documents#6of 40 · 1484LMArena · WebDevbuilding web apps and front ends#60of 133 · 1512Best attop three among current models
Where to use itprices checked 18 Nov 2026
API providers 3 · per 1M tokens, in / out
Host prices from OpenRouter; going direct can differ.
Facts and sources
Released23 Apr 2026
Announcementnot linked yet
Release entry–
Scored asGPT-5.5
Pro modeindex 177 · $30 / $180 per M
Output speed–
Hugging Faceclosed weights