tensor
.news
Integrity Index
Models
Compare
Labs
Papers
Methodology
About
← Labs
Mistral AI
12 models tracked · known for Mistral-7B-Instruct-v0.2, Mistral-7B-v0.1, Magistral Small 1.1
12
Models tracked
12
In our data
84.2
Best score
3
Notable
Models
Mistral NeMo
independently reproduced
84.2
Mixtral 8x7B
independently reproduced
83.07
Mistral Medium 3
independently reproduced
81.63
Mistral 7B v0.1
self-reported
75.2
Mistral Large 2 (Jul 2024)
independently reproduced
73.33
Mixtral 8x22B
independently reproduced
70.4
Mistral Large
independently reproduced
58.4
Mistral Large 2 (Nov 2024)
independently reproduced
50.28
Mistral Small 3.1
independently reproduced
46.77
Magistral Small 1.1
independently reproduced
31.23
Mistral-7B-Instruct-v0.2
unverified
—
Mistral-7B-v0.1
unverified
—
60 source records · huggingface_models, epoch_benchmarks. Every score is evidence-linked.
Follow the record
Other labs
Qwen
Meta AI
OpenAI
DeepSeek
NVIDIA
Google DeepMind
EleutherAI
Zhipu AI
Explore the record
Benchmark Integrity Index
Model Claim Ledger
Head-to-head comparisons