Mistral Large
Mistral Large is a closed AI model from Mistral with an index score of 100 (GPT-4 = 100), rank 195 of 217.
10084–117Index score#195 of 217 models
$2.0/ $6.0Price per million tokensinput / output · via OpenRouter
128KContext windowtokens it reads at once
26 Feb 2024ReleasedReplaced by Mistral Large 2
Where it sitson the frontier
GPT-4 (Jun 2023) reached this score 8 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsevidence
Professional workevidence
Novel problemsno evidence yet
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#195of 217 · 100
LMArena · Instruction followingfollowing detailed instructions#223of 362 · 1295LMArena · Creative writingcreative writing#223of 360 · 1276LMArena · Mathsmaths questions in chat#221of 346 · 1282LMArena · Textoverall chat quality, judged by people#232of 362 · 1306LMArena · Codingcoding questions in chat#230of 357 · 1346LMArena · Long promptslong, complex requests#233of 340 · 1305Epoch Capabilities Indexoverall capability from many benchmarks#162of 231 · 120.0Best attop three among current models
Replaced by Mistral Large 2; it no longer leads any category among current models.
Where to use itprices checked 18 Nov 2026
Host prices from OpenRouter; going direct can differ.
Facts and sources
Released26 Feb 2024
Announcementmistral.ai ↗
Release entryMistral Large
Scored asMistral Large
Output speed–
Hugging Faceclosed weights