Contamination MapText / LLM / Model
DeepSeek-R1-Distill
- Organisation
- DeepSeek-AI
- Family
- DeepSeek · version R1-Distill
- Released
- 2025-01-20 (Released with DeepSeek-R1 (DeepSeek API Docs news 'DeepSeek-R1 Release 2025/01/20'); HF repos created 2025-01-20)
- Checkpoints
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B, deepseek-ai/DeepSeek-R1-Distill-Qwen-7B, deepseek-ai/DeepSeek-R1-Distill-Qwen-14B, deepseek-ai/DeepSeek-R1-Distill-Qwen-32B, deepseek-ai/DeepSeek-R1-Distill-Llama-8B, deepseek-ai/DeepSeek-R1-Distill-Llama-70B
- Weights
- Open · MIT, plus base-model licenses (Apache 2.0 for Qwen2.5-based; Llama 3.1 / Llama 3.3 licenses for Llama-based)
- Links
- PaperModel card
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
“now finetuned with 800k samples curated with DeepSeek-R1.”
Other declared training data
-
DeepSeek-R1 800K supervised data (not yet matched to a dataset) · split: unknown · fine-tuning
Evidence
“now finetuned with 800k samples curated with DeepSeek-R1.”
huggingface.co · model card · License section · retrieved 2026-10-15 “using the 800k data described in Section B.3.3.”
arxiv.org · paper · Appendix B.4.3 · retrieved 2026-10-15
Declared exclusions
-
Dataset MMLU (Measuring Massive Multitask Language Understanding) · test portion excluded from fine-tuning data
Evidence
“To prevent benchmark contamination, we implemented comprehensive decontamination procedures for both pre-training and post-training data.”
arxiv.org · paper · Appendix D.1 (Decontamination) · retrieved 2026-10-15 “For post-training, mathematical SFT data and RL training prompts were sourced exclusively from pre-2023 competitions and underwent the same n-gram filtering protocol used in pre-training, ensuring no overlap between training and evaluation data.”
arxiv.org · paper · Appendix D.1 (Decontamination) · retrieved 2026-10-15 “Benchmarks We evaluate models on MMLU (Hendrycks et al., 2021), MMLU-Redux (Gema et al., 2025), MMLU-Pro (Wang et al., 2024),”
arxiv.org · paper · Appendix D.1 (Benchmarks) · retrieved 2026-10-15 -
Dataset MMLU-Pro · test portion excluded from fine-tuning data
Evidence
“To prevent benchmark contamination, we implemented comprehensive decontamination procedures for both pre-training and post-training data.”
arxiv.org · paper · Appendix D.1 (Decontamination) · retrieved 2026-10-15 “For post-training, mathematical SFT data and RL training prompts were sourced exclusively from pre-2023 competitions and underwent the same n-gram filtering protocol used in pre-training, ensuring no overlap between training and evaluation data.”
arxiv.org · paper · Appendix D.1 (Decontamination) · retrieved 2026-10-15 “Benchmarks We evaluate models on MMLU (Hendrycks et al., 2021), MMLU-Redux (Gema et al., 2025), MMLU-Pro (Wang et al., 2024),”
arxiv.org · paper · Appendix D.1 (Benchmarks) · retrieved 2026-10-15 -
Dataset GPQA Diamond · test portion excluded from fine-tuning data
Evidence
“To prevent benchmark contamination, we implemented comprehensive decontamination procedures for both pre-training and post-training data.”
arxiv.org · paper · Appendix D.1 (Decontamination) · retrieved 2026-10-15 “For post-training, mathematical SFT data and RL training prompts were sourced exclusively from pre-2023 competitions and underwent the same n-gram filtering protocol used in pre-training, ensuring no overlap between training and evaluation data.”
arxiv.org · paper · Appendix D.1 (Decontamination) · retrieved 2026-10-15 “GPQA Diamond (Rein et al., 2023), SimpleQA (OpenAI, 2024a), C-SimpleQA (He et al., 2024), SWE-Bench Verified (OpenAI, 2024b),”
arxiv.org · paper · Appendix D.1 (Benchmarks) · retrieved 2026-10-15 -
Dataset SWE-bench Verified · test portion excluded from fine-tuning data
Evidence
“To prevent benchmark contamination, we implemented comprehensive decontamination procedures for both pre-training and post-training data.”
arxiv.org · paper · Appendix D.1 (Decontamination) · retrieved 2026-10-15 “For post-training, mathematical SFT data and RL training prompts were sourced exclusively from pre-2023 competitions and underwent the same n-gram filtering protocol used in pre-training, ensuring no overlap between training and evaluation data.”
arxiv.org · paper · Appendix D.1 (Decontamination) · retrieved 2026-10-15 “GPQA Diamond (Rein et al., 2023), SimpleQA (OpenAI, 2024a), C-SimpleQA (He et al., 2024), SWE-Bench Verified (OpenAI, 2024b),”
arxiv.org · paper · Appendix D.1 (Benchmarks) · retrieved 2026-10-15 -
Dataset LiveCodeBench (code generation, release_v6) · test portion excluded from fine-tuning data
Evidence
“To prevent benchmark contamination, we implemented comprehensive decontamination procedures for both pre-training and post-training data.”
arxiv.org · paper · Appendix D.1 (Decontamination) · retrieved 2026-10-15 “For post-training, mathematical SFT data and RL training prompts were sourced exclusively from pre-2023 competitions and underwent the same n-gram filtering protocol used in pre-training, ensuring no overlap between training and evaluation data.”
arxiv.org · paper · Appendix D.1 (Decontamination) · retrieved 2026-10-15 “LiveCodeBench (Jain et al., 2024)”
arxiv.org · paper · Appendix D.1 (Benchmarks) · retrieved 2026-10-15 -
Dataset AIME 2024 · test portion excluded from fine-tuning data
Evidence
“To prevent benchmark contamination, we implemented comprehensive decontamination procedures for both pre-training and post-training data.”
arxiv.org · paper · Appendix D.1 (Decontamination) · retrieved 2026-10-15 “For post-training, mathematical SFT data and RL training prompts were sourced exclusively from pre-2023 competitions and underwent the same n-gram filtering protocol used in pre-training, ensuring no overlap between training and evaluation data.”
arxiv.org · paper · Appendix D.1 (Decontamination) · retrieved 2026-10-15 “American Invitational Mathematics Examination 2024 (AIME 2024) (MAA, 2024).”
arxiv.org · paper · Appendix D.1 (Benchmarks) · retrieved 2026-10-15 -
Dataset MATH-500 · test portion excluded from fine-tuning data
Evidence
“To prevent benchmark contamination, we implemented comprehensive decontamination procedures for both pre-training and post-training data.”
arxiv.org · paper · Appendix D.1 (Decontamination) · retrieved 2026-10-15 “For post-training, mathematical SFT data and RL training prompts were sourced exclusively from pre-2023 competitions and underwent the same n-gram filtering protocol used in pre-training, ensuring no overlap between training and evaluation data.”
arxiv.org · paper · Appendix D.1 (Decontamination) · retrieved 2026-10-15 “Finally, AIME, MATH-500, and CNMO 2024 comprise mathematics problems that test the model”
arxiv.org · paper · Appendix D.1 (Benchmarks) · 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
Dense models fine-tuned from Qwen2.5 (Math-1.5B, Math-7B, 14B, 32B), Llama-3.1-8B-Base and Llama-3.3-70B-Instruct; their pre-training data is that of those base models (see qwen2.5 entry; Qwen2.5-Math and Llama are not covered here).
Sources
- DeepSeek-R1 model card · model card · retrieved 2026-10-15
- DeepSeek-R1 paper (v2) · paper · retrieved 2026-10-15