Grok 4.5
Grok 4.5 is a closed AI model from xAI with an index score of 161 (GPT-4 = 100), rank 51 of 217.
161145–177Index score#51 of 217 models
$2.0/ $6.0Price per million tokensinput / output · via OpenRouter
500KContext windowtokens it reads at once
8 Jul 2026ReleasedReplaced by Grok 4.6
Where it sitson the frontier
GPT-5.2 reached this score 7 months 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#51of 217 · 161
LMArena · Creative writingcreative writing#31of 360 · 1452LMArena · Instruction followingfollowing detailed instructions#44of 362 · 1462LMArena · Long promptslong, complex requests#42of 340 · 1480LMArena · Codingcoding questions in chat#45of 357 · 1514LMArena · Textoverall chat quality, judged by people#48of 362 · 1466LMArena · Mathsmaths questions in chat#47of 346 · 1470LMArena · Visionunderstanding images#21of 145 · 1280Epoch Capabilities Indexoverall capability from many benchmarks#46of 231 · 155.0LMArena · Searchanswering with web search#13of 41 · 1216LMArena · WebDevbuilding web apps and front ends#48of 133 · 1552LMArena · Documentsworking with long documents#22of 40 · 1451Best attop three among current models
Where to use itprices checked 18 Nov 2026
API providers 1 · per 1M tokens, in / out
Host prices from OpenRouter; going direct can differ.
Facts and sources
Released8 Jul 2026
Announcementx.ai ↗
Release entryGrok 4.5
Scored asGrok 4.5
Output speed–
Hugging Faceclosed weights