Grok 4.6
Grok 4.6 is a closed AI model from xAI with an index score of 167 (GPT-4 = 100), rank 31 of 217.
167151–183Index score#31 of 217 models
$2.0/ $6.0Price per million tokensinput / output · via OpenRouter
500KContext windowtokens it reads at once
12 Aug 2026ReleasedReplaced by Grok 4.7
Where it sitson the frontier
GPT-5.5 reached this score 4 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#31of 217 · 167
Epoch Capabilities Indexoverall capability from many benchmarks#29of 231 · 157.8LMArena · Creative writingcreative writing#48of 360 · 1442LMArena · Long promptslong, complex requests#47of 340 · 1476LMArena · Instruction followingfollowing detailed instructions#54of 362 · 1451LMArena · Codingcoding questions in chat#56of 357 · 1508LMArena · Textoverall chat quality, judged by people#58of 362 · 1457LMArena · Mathsmaths questions in chat#75of 346 · 1445LMArena · WebDevbuilding web apps and front ends#30of 133 · 1618LMArena · Visionunderstanding images#34of 145 · 1263LiveBench · Overalloverall, on regularly refreshed questions#24of 38 · 63.5LMArena · Documentsworking with long documents#27of 40 · 1438Best attop three among current models
Replaced by Grok 4.7; it no longer leads any category among current models.
Where to use itprices checked 18 Nov 2026
API providers 2 · per 1M tokens, in / out
Host prices from OpenRouter; going direct can differ.
Facts and sources
Released12 Aug 2026
Announcementx.ai ↗
Release entryGrok 4.6
Scored asGrok 4.6
Output speed–
Hugging Faceclosed weights