Contamination Map Methodology

Text / LLM / Model

Mistral 7B

Organisation
Mistral AI
Family
Mistral · version v0.1
Released
2023-09-27 (Mistral AI blog 'Mistral 7B' dated September 27, 2023 (https://mistral.ai/news/announcing-mistral-7b))
Checkpoints
mistralai/Mistral-7B-v0.1, mistralai/Mistral-7B-Instruct-v0.1
Weights
Open · Apache 2.0
Links
PaperModel cardCode

Training data disclosure: Vague

Level determined for 0% of benchmark cells.

“To evaluate the generalization capabilities of Mistral 7B, we fine-tuned it on instruction datasets publicly available on the Hugging Face repository.”
arxiv.org · paper · Section 4 Instruction Finetuning · retrieved 2026-10-15

Other declared training data

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

Pre-training data is not described at all in the paper, blog or model card; 'vague' reflects only the fine-tuning description. Later Mistral 7B checkpoints (Instruct-v0.2, v0.3) are separate releases not covered here. Third-party signal on HellaSwag (indirect, not shown as a cell): Sample-specific contamination detected on HellaSwag (p < 0.5%, estimated effect 3-8%). Third-party signal on GSM8K (Grade School Math 8K) (indirect, not shown as a cell): Sample-specific contamination detected on GSM8K (p < 0.5%, estimated effect 3-8%). Third-party signal on TruthfulQA (indirect, not shown as a cell): 8.5 percentage points higher on TruthfulQA than on the retro-holdout. Performance gap on a fresh holdout is evidence of benchmark inflation/overfitting, not proof of test-set inclusion.

Sources