{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "jiang-et-al-mixtral-2024",
    "title": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model",
    "summary": "Released and evaluated Mixtral 8x7B, routing each token through two of eight feed-forward experts per layer with a reduced active-parameter count.",
    "boundary": "The company announced the model in December 2023; this record uses the January 2024 paper year. Reported benchmark comparisons are setup-specific.",
    "area": "Mixture-of-experts language models",
    "topic": "Artificial intelligence",
    "year": 2024,
    "lane": "HUMAN",
    "result": "EMPIRICAL",
    "package_id": "jiang-et-al-mixtral-2024",
    "target": {
      "record_id": "urn:uuid:a63d71fc-6924-4a60-a217-aafa31e13bc3",
      "version": 1,
      "content_hash": "sha256:0a858c77f38a7b841f219ebd810240579f32d6bb71532fac129786da3bd6baf4"
    },
    "humans": [
      "Albert Q. Jiang",
      "Alexandre Sablayrolles",
      "Antoine Roux",
      "Arthur Mensch",
      "Blanche Savary",
      "Chris Bamford",
      "Devendra Singh Chaplot",
      "Diego de las Casas",
      "Emma Bou Hanna",
      "Florian Bressand",
      "Gianna Lengyel",
      "Guillaume Bour",
      "Guillaume Lample",
      "Lélio Renard Lavaud",
      "Lucile Saulnier",
      "Marie-Anne Lachaux",
      "Pierre Stock",
      "Sandeep Subramanian",
      "Sophia Yang",
      "Szymon Antoniak",
      "Teven Le Scao",
      "Théophile Gervet",
      "Thibaut Lavril",
      "Thomas Wang",
      "Timothée Lacroix",
      "William El Sayed"
    ],
    "authors_complete": true,
    "human_role_note": "Complete named paper byline. Human research, source-reported system execution and experimental validation are distinct; individual effort shares are not measured.",
    "agents": [],
    "related": [],
    "subresults": [],
    "scientific_assessment": {
      "source_review": "SOURCE_CURATED",
      "scientific_review": "NOT_REVIEWED_BY_WRS",
      "formal_replay": "NOT_RUN",
      "provider_attestation": "NONE"
    },
    "sources": [
      {
        "id": "arxiv-2401-04088",
        "title": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
        "url": "https://arxiv.org/abs/2401.04088v1"
      },
      {
        "id": "company-jiang-et-al-mixtral-2024",
        "title": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — official company source",
        "url": "https://mistral.ai/news/mixtral-of-experts/"
      }
    ],
    "points": "18000",
    "published_grade": {
      "id": "jiang-et-al-mixtral-2024",
      "entry_id": "jiang-et-al-mixtral-2024",
      "band": "B",
      "modifier": null,
      "target": {
        "record_id": "urn:uuid:a63d71fc-6924-4a60-a217-aafa31e13bc3",
        "version": 1,
        "content_hash": "sha256:0a858c77f38a7b841f219ebd810240579f32d6bb71532fac129786da3bd6baf4"
      },
      "what_changed": "Released and evaluated Mixtral 8x7B, routing each token through two of eight feed-forward experts per layer with a reduced active-parameter count.",
      "scope": "Released and evaluated Mixtral 8x7B, routing each token through two of eight feed-forward experts per layer with a reduced active-parameter count. Scope limitation: The company announced the model in December 2023; this record uses the January 2024 paper year. Reported benchmark comparisons are setup-specific.",
      "status": "PROVISIONAL_EDITORIAL",
      "scientific_correctness_certified": false
    },
    "assessment_disposition": {
      "status": "ASSESSED",
      "label": "Provisionally assessed",
      "reason": "A current grade and separate reference score identify this exact contribution.",
      "target": {
        "record_id": "urn:uuid:a63d71fc-6924-4a60-a217-aafa31e13bc3",
        "version": 1,
        "content_hash": "sha256:0a858c77f38a7b841f219ebd810240579f32d6bb71532fac129786da3bd6baf4"
      },
      "edition": "ratings-e039106f30dec177"
    }
  },
  "version": {
    "kind": "PUBLIC_RECORD_VIEW",
    "previous": null,
    "published_at": "2026-09-27T00:00:00Z",
    "publisher": {
      "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33",
      "role": "WRS_EDITORIAL_PUBLICATION"
    },
    "record": {
      "contributors": [
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Albert Q. Jiang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Alexandre Sablayrolles",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Antoine Roux",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Arthur Mensch",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Blanche Savary",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Chris Bamford",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Devendra Singh Chaplot",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Diego de las Casas",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Emma Bou Hanna",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Florian Bressand",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Gianna Lengyel",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Guillaume Bour",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Guillaume Lample",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Lélio Renard Lavaud",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Lucile Saulnier",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Marie-Anne Lachaux",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Pierre Stock",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Sandeep Subramanian",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Sophia Yang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Szymon Antoniak",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Teven Le Scao",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Théophile Gervet",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Thibaut Lavril",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Thomas Wang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Timothée Lacroix",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "William El Sayed",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
            "url": "https://arxiv.org/abs/2401.04088v1"
          }
        },
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-1",
          "kind": "source_reference",
          "source": {
            "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — official company source",
            "url": "https://mistral.ai/news/mixtral-of-experts/"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "The company announced the model in December 2023; this record uses the January 2024 paper year. Reported benchmark comparisons are setup-specific.",
        "domain": "Mixture-of-experts language models"
      },
      "sources": [
        {
          "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
          "url": "https://arxiv.org/abs/2401.04088v1"
        },
        {
          "citation": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — official company source",
          "url": "https://mistral.ai/news/mixtral-of-experts/"
        }
      ],
      "statement": "# Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model\n\nReleased and evaluated Mixtral 8x7B, routing each token through two of eight feed-forward experts per layer with a reduced active-parameter count.\n\n## Scientific scope\n\nThe company announced the model in December 2023; this record uses the January 2024 paper year. Reported benchmark comparisons are setup-specific.\n\n## Reading status\n\nThis is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.\n\n## People and systems\n\nAlbert Q. Jiang; Alexandre Sablayrolles; Antoine Roux; Arthur Mensch; Blanche Savary; Chris Bamford; Devendra Singh Chaplot; Diego de las Casas; Emma Bou Hanna; Florian Bressand; Gianna Lengyel; Guillaume Bour; Guillaume Lample; Lélio Renard Lavaud; Lucile Saulnier; Marie-Anne Lachaux; Pierre Stock; Sandeep Subramanian; Sophia Yang; Szymon Antoniak; Teven Le Scao; Théophile Gervet; Thibaut Lavril; Thomas Wang; Timothée Lacroix; William El Sayed\n\nComplete named paper byline. Human research, source-reported system execution and experimental validation are distinct; individual effort shares are not measured.\n\n\n\n## Original sources\n\n- [Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper](https://arxiv.org/abs/2401.04088v1)\n- [Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — official company source](https://mistral.ai/news/mixtral-of-experts/)\n",
      "summary": "Released and evaluated Mixtral 8x7B, routing each token through two of eight feed-forward experts per layer with a reduced active-parameter count.",
      "title": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model"
    },
    "record_id": "urn:uuid:a63d71fc-6924-4a60-a217-aafa31e13bc3",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:a63d71fc-6924-4a60-a217-aafa31e13bc3",
      "version": 1,
      "content_hash": "sha256:0a858c77f38a7b841f219ebd810240579f32d6bb71532fac129786da3bd6baf4"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:f2e5617105e434dad9fbd22ea7e317c344cafb44eb1d095810e2b51e9fec7f21"
  },
  "target": {
    "record_id": "urn:uuid:a63d71fc-6924-4a60-a217-aafa31e13bc3",
    "version": 1,
    "content_hash": "sha256:0a858c77f38a7b841f219ebd810240579f32d6bb71532fac129786da3bd6baf4"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "jiang-et-al-mixtral-2024",
    "entry_id": "jiang-et-al-mixtral-2024",
    "revision": 1,
    "title": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model",
    "context": "Mixture-of-experts language models",
    "track": "Human-designed AI research method or resource",
    "band": "B",
    "modifier": null,
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-09-27",
    "evidence_cutoff": "2026-09-27",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Released and evaluated Mixtral 8x7B, routing each token through two of eight feed-forward experts per layer with a reduced active-parameter count.",
    "scope": "Released and evaluated Mixtral 8x7B, routing each token through two of eight feed-forward experts per layer with a reduced active-parameter count. Scope limitation: The company announced the model in December 2023; this record uses the January 2024 paper year. Reported benchmark comparisons are setup-specific.",
    "evidence_summary": "The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. The company announced the model in December 2023; this record uses the January 2024 paper year. Reported benchmark comparisons are setup-specific.",
    "references": [
      {
        "title": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — original paper",
        "url": "https://arxiv.org/abs/2401.04088v1",
        "locator": "Abstract and complete bibliographic byline for 2401.04088v1; not an independent proof or experimental replication."
      },
      {
        "title": "Jiang and colleagues: Mixtral 8x7B sparse mixture-of-experts model — official company source",
        "url": "https://mistral.ai/news/mixtral-of-experts/",
        "locator": "Source-linked contribution and stated scientific limits; not an independent replication."
      }
    ],
    "roles": [
      {
        "who": "The named authors listed in the linked research record",
        "credit": "SCIENCE",
        "did": "Complete source byline retained in the research record; human research direction, method development and evaluation. Individual labor shares are not measured."
      }
    ],
    "target": {
      "record_id": "urn:uuid:a63d71fc-6924-4a60-a217-aafa31e13bc3",
      "version": 1,
      "content_hash": "sha256:0a858c77f38a7b841f219ebd810240579f32d6bb71532fac129786da3bd6baf4"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "18000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}