Contamination MapText / LLM / Model
Claude 3 (Opus, Sonnet, Haiku)
- Organisation
- Anthropic
- Family
- Claude · version 3
- Released
- 2024-03-04 (anthropic.com/news/claude-3-family announcement dated Mar 4, 2024)
- Training cutoff
- 2023-08-01
Evidence
“The knowledge cutoff for the Claude 3 models is August 2023.”
www-cdn.anthropic.com · model card · Section 1 · retrieved 2026-10-15 “Claude 3 models are trained on a proprietary mix of publicly available information on the Internet as of August 2023, as well as non-public data from third parties, data provided by data labeling services and paid contractors, and data we generate internally.”
www-cdn.anthropic.com · model card · Section 2.5 (Training Data) · retrieved 2026-10-15 - Checkpoints
- claude-3-opus-20240229, claude-3-sonnet-20240229, claude-3-haiku-20240307
- Weights
- Closed · proprietary
- Links
- Model card
Training data disclosure: Vague
Level determined for 13% of benchmark cells.
- TestTest data seen0
- SeenSeen, split unclear0
- TrainTraining data seen0
- Related data seen0
- NoNot seen3
- ?Unknown19
“Claude 3 models are trained on a proprietary mix of publicly available information on the Internet as of August 2023, as well as non-public data from third parties, data provided by data labeling services and paid contractors, and data we generate internally.”
Other declared training data
-
publicly available information on the Internet as of August 2023 (broad web data: may contain benchmark test sets) · split: unknown
Evidence
“Claude 3 models are trained on a proprietary mix of publicly available information on the Internet as of August 2023, as well as non-public data from third parties, data provided by data labeling services and paid contractors, and data we generate internally.”
www-cdn.anthropic.com · model card · Section 2.5 (Training Data) · retrieved 2026-10-15 -
non-public data from third parties (not yet matched to a dataset) · split: unknown
Evidence
“Claude 3 models are trained on a proprietary mix of publicly available information on the Internet as of August 2023, as well as non-public data from third parties, data provided by data labeling services and paid contractors, and data we generate internally.”
www-cdn.anthropic.com · model card · Section 2.5 (Training Data) · retrieved 2026-10-15 -
data provided by data labeling services and paid contractors (not yet matched to a dataset) · split: unknown
Evidence
“Claude 3 models are trained on a proprietary mix of publicly available information on the Internet as of August 2023, as well as non-public data from third parties, data provided by data labeling services and paid contractors, and data we generate internally.”
www-cdn.anthropic.com · model card · Section 2.5 (Training Data) · retrieved 2026-10-15 -
data we generate internally (not yet matched to a dataset) · split: unknown
Evidence
“Claude 3 models are trained on a proprietary mix of publicly available information on the Internet as of August 2023, as well as non-public data from third parties, data provided by data labeling services and paid contractors, and data we generate internally.”
www-cdn.anthropic.com · model card · Section 2.5 (Training Data) · 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
Multimodal LLM benchmarks
Unknown MMMU (Massive Multi-discipline Multimodal Understanding and Reasoning) · training data not disclosed in enough detail
Unknown MMMU-Pro · training data not disclosed in enough detail
Unknown MathVista · training data not disclosed in enough detail
Unknown ChartQA · training data not disclosed in enough detail
Unknown DocVQA · training data not disclosed in enough detail
Unknown AI2D (AI2 Diagrams) · training data not disclosed in enough detail
Not seen CharXiv · its test items were published from 2024-06-26, after the model's stated training-data cutoff (2023-08-01)
Evidence (4)
“The knowledge cutoff for the Claude 3 models is August 2023.”
“Claude 3 models are trained on a proprietary mix of publicly available information on the Internet as of August 2023, as well as non-public data from third parties, data provided by data labeling services and paid contractors, and data we generate internally.”
“arXiv:2406.18521v1 [cs.CL] 26 Jun 2024”
“we release all QA pairs for the validation set and keep the answers to the test set private to prevent data leakage.”
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
Not seen AIME 2024 · its test items were published from 2024-01-31, after the model's stated training-data cutoff (2023-08-01)
Evidence (5)
“The knowledge cutoff for the Claude 3 models is August 2023.”
“Claude 3 models are trained on a proprietary mix of publicly available information on the Internet as of August 2023, as well as non-public data from third parties, data provided by data labeling services and paid contractors, and data we generate internally.”
“2024 AIME I problems and solutions. The test was held on Wednesday, January 31 – Thursday, February 1, 2024.”
“AIME I (main AIME competition date): Thursday, Feb. 1, 2024 between 1:30 pm ET and 5:30 pm ET.”
“AIME II (alternate AIME competition date): Wednesday, Feb. 7, 2024 between 1:30 pm ET and 5:30 pm ET.”
Not seen AIME 2025 · its test items were published from 2025-02-06, after the model's stated training-data cutoff (2023-08-01)
Evidence (4)
“The knowledge cutoff for the Claude 3 models is August 2023.”
“Claude 3 models are trained on a proprietary mix of publicly available information on the Internet as of August 2023, as well as non-public data from third parties, data provided by data labeling services and paid contractors, and data we generate internally.”
“2025 AIME I problems and solutions. The test was held on Thursday, February 6, 2025.”
“This year the AIME I will take place on February 6, 2025, while the alternate AIME II will take place on February 12, 2025.”
Unknown MATH-500 · training data not disclosed in enough detail
Notes
The model card states the Claude 3 models were not trained on user prompt or output data. No contamination or decontamination statement found in the model card. Accepts image input: “The Claude 3 family of models are multimodal (image and video-frame input)”
Sources
- The Claude 3 Model Family: Opus, Sonnet, Haiku (model card) · model card · retrieved 2026-10-15
- Introducing the next generation of Claude · website · retrieved 2026-10-15
- Claude docs: Model deprecations (model IDs) · website · retrieved 2026-10-15