Mistral-Large-3-675B-Instruct-2512
Mistral AI- Arena score
- 1429
- Among open models
- #24of 148
- Among all on Arena
- #98
- Votes
- 88,567
Measured on Mistral Large 3, the served version, not a local build. LMArena, CC BY 4.0, published Nov 11, 2026.
Score by category
CategoryScoreOpen rankArena rankVotes
- French1455#19#732.6K
- Software & IT1451#29#10233K
- Coding1449#31#10722.3K
- Medicine & health1447#26#856.2K
- Science1446#24#9014.4K
- Chinese1446#42#1376.7K
- Polish1441#14#641.9K
- Legal & government1441#20#886.7K
- English1440#26#9936.5K
- German1439#18#781.5K
- Hard prompts, English1437#33#11422.4K
- Spanish1436#24#902.7K
- Hard prompts1431#31#11354.3K
- Multi-turn1429#24#10514.8K
- Applied math1425#41#1294.7K
- Expert1422#43#1358.4K
- Excluding ties1421#24#9965.1K
- Business & finance1418#31#10616.4K
- Math1416#40#1365K
- Long prompts1415#34#12133.8K
- Non-English1414#24#10052.1K
- Russian1412#28#11510.8K
- Instructions1405#33#12028.7K
- Writing & literature1397#32#12022.3K
- Japanese1397#19#871K
- Korean1390#19#871.4K
- Media & sports1387#32#12219.8K
- Creative writing1386#31#12816.1K
About as strong, smaller
Compare
gemma-4-26B-A4B-itGoogle143425.8B

Qwen3.8-27BQwen143727.8B

gemma-4-31B-itGoogle144331.3B

Qwen3-Next-80B-A3B-InstructQwen141781.3B
Built on it
Ways to run it
Most downloaded
- Mistral-Large-3-675B-Instruct-2512-GGUFunsloth · Quantization4.1K downloads
- mistralai_Mistral-Large-3-675B-Instruct-2512-GGUFbartowski · Quantization1.7K downloads
- Mistral-Large-3-675B-Instruct-2512-GGUFmradermacher · Quantization563 downloads
- mistralai.Mistral-Large-3-675B-Instruct-2512-GGUFDevQuasar · Quantization420 downloads
- Mistral-Large-3-675B-Instruct-2512-i1-GGUFmradermacher · Quantization279 downloads
BenchClub runs
Not runnable yet
Runs open once a Mistral-Large-3-675B-Instruct-2512 build is registered.
More from Mistral AI
See more
Mistral-Large-4-1T-A52B18K—

Mistral-Medium-3.5-128B14.3K128B

Mistral-7B-Instruct-v0.21.1M7.2B

Mistral-7B-v0.1440.8K7.2B
Other >300B models
See more
DeepSeek-V3.2DeepSeek9.6M685B
GLM-5.3-FlashZ.ai6.4M321B
InklingThinking Machines1.5M952B
NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16NVIDIA1M561B