← All lab files

Mistral research file

#7 on the current provider board.

Mistral Medium 3.5 scores 1427.3 according to LMArena's text style-control snapshot published July 16, 2026.

LMArena source rank#7
LMArena rating1427.3
Reported interval1420.7–1433.9
Battles11,017

Model records from the Epoch AI catalog

Mistral models in the reviewed record.

Release date, domains, tasks, access, and weight availability come from the Epoch AI catalog. These fields describe models but do not rank them.

  1. Mistral OCR

    Multimodal, Vision, LanguageAPI accessClosed weightsRead profile →

  2. Pixtral Large

    Multimodal, Language, VisionOpen weights (non-commercial)Open weightsRead profile →

  3. Mistral Large 2

    LanguageOpen weights (non-commercial)Open weightsOpen record →

  4. Mathstral

    Mathematics, LanguageOpen weights (unrestricted)Open weightsOpen record →

  5. Mistral Large

    LanguageAPI accessClosed weightsOpen record →

  6. Mixtral 8x7B

    LanguageOpen weights (unrestricted)Open weightsOpen record →

Filter every reviewed record in the model explorer →

Historical momentum · legacy metric only

+419.4 from first to last sampled observation.

This change is calculated only inside the selected legacy series, from October 2, 2023 to August 29, 2025. The archive crosses methodology changes and cannot be joined to, trended into, or compared numerically with the current snapshot.

First sample1014.0mistral-7b-instruct
Legacy peak1433.42025-08-29 · mistral-medium-2508
Last sample1433.4mistral-medium-2508
Show all 9 legacy observations
  1. mistral-7b-instruct1014.0
  2. mixtral-8x7b-instruct-v0.11068.3
  3. mistral-large-24021080.7
  4. mistral-large-24021156.9
  5. mistral-large-24071249.8
  6. mistral-large-24071251.4
  7. mistral-large-24071251.6
  8. mistral-medium-25051339.0
  9. mistral-medium-25081433.4

Release record

Latest matched notable models.

Epoch AI records provide dated context only. A release record does not imply a score change.

  1. Mistral OCR
  2. Pixtral Large
  3. Mistral Large 2
  4. Mathstral
  5. Mistral Large

Continue researching

Profiles, guides, and reports.

Evidence boundary

Three sources. Three distinct jobs.

Current frontier: LMArena leaderboard dataset, revision afed939e10281b660a4369206ca505b2bf5e0208, CC BY 4.0.

Historical context: LMArena historical Space artifacts, with one SHA-256 receipt per selected sample and no continuity to the current metric.

Catalog and releases: Epoch AI notable models. No corporate profile is added because our sources do not establish company-level facts beyond model authorship.

Read the full methodology