tensor.news
Integrity IndexModelsCompareLabsPapersMethodologyAbout
tensor.news

© 2026

Evidence

  • Integrity Index
  • Model Claim Ledger
  • Compare

Entities

  • Models
  • Benchmarks
  • Labs
  • Papers

Method

  • Methodology
  • About
  • Privacy

Machine

  • Feed (Atom)
  • llms.txt
  • llms-full.txt
  • Sitemap

tensor.news grades benchmarks and tags model claims by evidence status. Every fact carries a source record and provenance. Scores are framed as task performance under a disclosed harness, never as deployed capability.

← 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 NeMoindependently reproduced84.2Mixtral 8x7Bindependently reproduced83.07Mistral Medium 3independently reproduced81.63Mistral 7B v0.1self-reported75.2Mistral Large 2 (Jul 2024)independently reproduced73.33Mixtral 8x22Bindependently reproduced70.4Mistral Largeindependently reproduced58.4Mistral Large 2 (Nov 2024)independently reproduced50.28Mistral Small 3.1independently reproduced46.77Magistral Small 1.1independently reproduced31.23Mistral-7B-Instruct-v0.2unverified—Mistral-7B-v0.1unverified—
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