Grok 4.7
Grok 4.7 is a closed AI model from xAI with an index score of 164 (GPT-4 = 100), rank 37 of 217.
164149–180Index score#37 of 217 models
$2.0/ $6.0Price per million tokensinput / output · via OpenRouter
500KContext windowtokens it reads at once
21 Sep 2026Released2 months ago
Where it sitson the frontier
Claude Opus 4.6 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 11 leaderboards
The Model Indexthird-party tests, our method#37of 217 · 164
Epoch Capabilities Indexoverall capability from many benchmarks#37of 231 · 156.4LMArena · WebDevbuilding web apps and front ends#22of 133 · 1640LMArena · Creative writingcreative writing#71of 360 · 1421LMArena · Instruction followingfollowing detailed instructions#76of 362 · 1435LMArena · Textoverall chat quality, judged by people#77of 362 · 1443LMArena · Mathsmaths questions in chat#74of 346 · 1447LMArena · Long promptslong, complex requests#73of 340 · 1454LMArena · Codingcoding questions in chat#81of 357 · 1493LMArena · Visionunderstanding images#47of 145 · 1249LiveBench · Overalloverall, on regularly refreshed questions#19of 38 · 67.9Best attop three among current models
Not in the top three among current models on any category we track.
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
Released21 Sep 2026
Announcementx.ai ↗
Release entryGrok 4.7
Scored asGrok 4.7
Output speed–
Hugging Faceclosed weights