Grok-3 mini
Grok-3 mini is a closed AI model from xAI with an index score of 131 (GPT-4 = 100), rank 127 of 217.
131115–146Index score#127 of 217 models
–Price per million tokensno public API price found
–Context windowtokens it reads at once
9 Apr 2025Released1 year 7 months ago
Where it sitson the frontier
o1 reached this score 4 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsno evidence yet
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 8 leaderboards
The Model Indexthird-party tests, our method#127of 217 · 131
LMArena · Mathsmaths questions in chat#146of 346 · 1389LMArena · Instruction followingfollowing detailed instructions#160of 362 · 1360LMArena · Textoverall chat quality, judged by people#164of 362 · 1364LMArena · Creative writingcreative writing#165of 360 · 1332LMArena · Long promptslong, complex requests#159of 340 · 1377LMArena · Codingcoding questions in chat#179of 357 · 1393Epoch Capabilities Indexoverall capability from many benchmarks#119of 231 · 139.9Best 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
Host prices from OpenRouter; going direct can differ.
Facts and sources
Released9 Apr 2025
Announcementnot linked yet
Release entry–
Scored asGrok-3 mini
Output speed–
Hugging Faceclosed weights