GPT-4.1
GPT-4.1 is a closed AI model from OpenAI with an index score of 126 (GPT-4 = 100), rank 142 of 217.
126110–142Index score#142 of 217 models
$2.0/ $8.0Price per million tokensinput / output · via OpenRouter
1.05MContext windowtokens it reads at once
14 Apr 2025ReleasedReplaced by GPT-5
Where it sitson the frontier
o1 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 9 leaderboards
The Model Indexthird-party tests, our method#142of 217 · 126
LMArena · Creative writingcreative writing#87of 360 · 1403LMArena · Textoverall chat quality, judged by people#117of 362 · 1415LMArena · Long promptslong, complex requests#111of 340 · 1426LMArena · Instruction followingfollowing detailed instructions#119of 362 · 1403LMArena · Codingcoding questions in chat#127of 357 · 1456LMArena · Mathsmaths questions in chat#156of 346 · 1375LMArena · Visionunderstanding images#72of 145 · 1214Epoch Capabilities Indexoverall capability from many benchmarks#127of 231 · 136.2Best attop three among current models
Replaced by GPT-5; 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
Released14 Apr 2025
Announcementen.wikipedia.org ↗
Release entryGPT-4.1
Scored asGPT-4.1
Output speed–
Hugging Faceclosed weights