Set test set as contaminated

add PR number

Likely FLORES contamination for Claude 3 Opus

Add reports from Benchmarking paper "Benchmark Leakage in Large Language Models" (#27)

Add Reports Based on "Llemma: An Open Language Model For Mathematics" (#23)

add flores contamination in xP3 (#20)

Add Aquila model series which have gsm8k test set contamination (#21)

GPT-3.5 Spider contamination based on https://arxiv.org/pdf/2402.08100 (#18)

Updates

Add changes

Superglue/RealNews Contamination based on "Noise-Robust De-Duplication at Scale" (#15)

Mistral 7B Arc Easy Contamination based on "Proving Test Set Contamination in Black Box Language Models" (#14)

Added Contamination Evidence from GPT4 Tech Report using String matching on GPT-4 (#11)

GPT-3.5Turbo HumanEval Contamination based on "Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models" (#16)

Added Contamination Evidence on MMLU of ChatGPT/GPT4 from "Investigating data contamination in modern benchmarks for large language models" (#10)

Added Contamination Info on Old Models: GPT3, FLAN, GLaM, PaLM, PaLM 2 (#13)

Contamination results based on "Data Contamination Quiz" (#9)

Fix arxiv links

Code contamination in HumanEval and MBPP (#12)

Add model-based results for MedNLI, RadNLI for GPT-3.5 and GPT-4 (#8)

Add data from "An Open-Source Data Contamination Report for Large Language Models" (#5)

Import data from LM Contamination Index (#7)

Fix format issues

Add data from "Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus" (#6)

Add reports from Time Travel In LLMs paper (#3)

Fix super_glue replace

Add PR links to previous commits

Add data from WIMBD paper (#2)

Small changes

Initital commit