Contamination MapText / LLM / Model
Mixtral 8x7B
- Organisation
- Mistral AI
- Family
- Mistral · version v0.1
- Released
- 2023-12-11 (Mistral AI blog 'Mixtral of experts' dated December 11, 2023 (https://mistral.ai/news/mixtral-of-experts))
- Checkpoints
- mistralai/Mixtral-8x7B-v0.1, mistralai/Mixtral-8x7B-Instruct-v0.1
- Weights
- Open · Apache 2.0
- Links
- PaperModel cardCode
Training data disclosure: Vague
Level determined for 0% of benchmark cells.
- TestTest data seen0
- SeenSeen, split unclear0
- TrainTraining data seen0
- Related data seen0
- NoNot seen0
- ?Unknown15
“Mixtral is pre-trained on data extracted from the open Web – we train experts and routers simultaneously.”
“Mixtral is pretrained with multilingual data using a context size of 32k tokens.”
Other declared training data
-
data extracted from the open Web (broad web data: may contain benchmark test sets) · split: unknown
Evidence
“Mixtral is pre-trained on data extracted from the open Web – we train experts and routers simultaneously.”
mistral.ai · website · Blog body · retrieved 2026-10-15 “Compared to Mistral 7B, we significantly upsample the proportion of multilingual data during pretraining.”
arxiv.org · paper · Section 3.1 Multilingual benchmarks · retrieved 2026-10-15 -
an instruction dataset (SFT) (not yet matched to a dataset) · split: unknown · fine-tuning
Not named.
Evidence
“We train Mixtral – Instruct using supervised fine-tuning (SFT) on an instruction dataset followed by Direct Preference Optimization (DPO) [25] on a paired feedback dataset.”
arxiv.org · paper · Section 4 Instruction Fine-tuning · retrieved 2026-10-15 -
a paired feedback dataset (DPO) (not yet matched to a dataset) · split: unknown · fine-tuning
Not named.
Evidence
“We train Mixtral – Instruct using supervised fine-tuning (SFT) on an instruction dataset followed by Direct Preference Optimization (DPO) [25] on a paired feedback dataset.”
arxiv.org · paper · Section 4 Instruction Fine-tuning · retrieved 2026-10-15
Benchmark cells
Classic LLM benchmarks
Unknown MMLU (Measuring Massive Multitask Language Understanding) · training data not disclosed in enough detail
Unknown GSM8K (Grade School Math 8K) · training data not disclosed in enough detail
Unknown MATH (Mathematics Aptitude Test of Heuristics) · training data not disclosed in enough detail
Unknown HumanEval · training data not disclosed in enough detail
Unknown ARC-Challenge (AI2 Reasoning Challenge, Challenge Set) · training data not disclosed in enough detail
Unknown HellaSwag · training data not disclosed in enough detail
Unknown TruthfulQA · training data not disclosed in enough detail
Unknown WinoGrande · training data not disclosed in enough detail
Recent LLM benchmarks
Unknown GPQA Diamond · training data not disclosed in enough detail
Unknown MMLU-Pro · training data not disclosed in enough detail
Unknown LiveCodeBench (code generation, release_v6) · training data not disclosed in enough detail
Unknown SWE-bench Verified · training data not disclosed in enough detail
Unknown AIME 2024 · training data not disclosed in enough detail
Unknown AIME 2025 · training data not disclosed in enough detail
Unknown MATH-500 · training data not disclosed in enough detail
Notes
No contamination analysis or decontamination statement.
Sources
- Mixtral of Experts (arXiv v1) · paper · retrieved 2026-10-15
- Mixtral of experts (Mistral AI blog) · website · retrieved 2026-10-15
- Mixtral-8x7B-v0.1 model card · model card · retrieved 2026-10-15
- Mixtral-8x7B-Instruct-v0.1 model card · model card · retrieved 2026-10-15