Mistral Large 2
Mistral Large 2 is an open-weights AI model from Mistral with an index score of 109 (GPT-4 = 100), rank 180 of 217.
10992–125Index score#180 of 217 models
–Price per million tokensno public API price found
–Context windowtokens it reads at once
24 Jul 2024ReleasedReplaced by Mistral Large 2 (Nov 2024)
Where it sitson the frontier
GPT-4o reached this score 2 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingno evidence yet
Agentsevidence
Professional workno evidence yet
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#180of 217 · 109
LMArena · Creative writingcreative writing#210of 360 · 1287LMArena · Instruction followingfollowing detailed instructions#220of 362 · 1299LMArena · Textoverall chat quality, judged by people#224of 362 · 1315LMArena · Mathsmaths questions in chat#215of 346 · 1288LMArena · Codingcoding questions in chat#222of 357 · 1354Epoch Capabilities Indexoverall capability from many benchmarks#150of 231 · 126.4LMArena · Long promptslong, complex requests#234of 340 · 1305Best attop three among current models
Replaced by Mistral Large 2 (Nov 2024); it no longer leads any category among current models.
Facts and sources
Released24 Jul 2024
Announcementmistral.ai ↗
Release entryMistral Large 2
Scored asMistral Large 2 (Jul 2024)
Output speed–
Hugging Facenot linked