# Contamination detection on BenchMarker Source: [Contamination detection on BenchMarker]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:30:50.949Z Evaluation of model performance on contamination detection using the BenchMarker dataset, reporting Accuracy, F1 Score, and Cohen’s κ. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Contamination detection | | Dataset (including any stated split) | BenchMarker | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Accuracy](): Higher is better; unit: PERCENT. - [F1 Score](): Higher is better; unit: PERCENT. - [Cohen's Kappa](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Google + GPT-5 | 71.2 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Google + Gemini Pro | 69.9 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Google + Claude Sonnet | 69 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Serper + GPT-5 | 67.6 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Perplexity + GPT-5 | 64.2 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Exa + GPT-5 | 59 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Tavily + GPT-5 | 58.1 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Brave + GPT-5 | 54.2 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Always Flawed | 53.7 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Random (50/50) | 50 | Not recorded | 69896a28c97a0b3e3b5dc5ac | | Always Not Flawed | 46.3 | Not recorded | 69896a28c97a0b3e3b5dc5ac | ### Google + GPT-5 Accuracy: 71.2. Result ID: 699646735698665ec48a55f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Search API":"Google","LLM Backbone":"GPT-5"}. This record does not assert independent reproduction. ### Google + Gemini Pro Accuracy: 69.9. Result ID: 699646735698665ec48a55ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Search API":"Google","LLM Backbone":"Gemini Pro"}. This record does not assert independent reproduction. ### Google + Claude Sonnet Accuracy: 69. Result ID: 699646735698665ec48a55f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Search API":"Google","LLM Backbone":"Claude Sonnet"}. This record does not assert independent reproduction. ### Serper + GPT-5 Accuracy: 67.6. Result ID: 699646735698665ec48a55f6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Search API":"Serper","LLM Backbone":"GPT-5"}. This record does not assert independent reproduction. ### Perplexity + GPT-5 Accuracy: 64.2. Result ID: 699646735698665ec48a55f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Search API":"Perplexity","LLM Backbone":"GPT-5"}. This record does not assert independent reproduction. ### Exa + GPT-5 Accuracy: 59. Result ID: 699646735698665ec48a55f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Search API":"Exa","LLM Backbone":"GPT-5"}. This record does not assert independent reproduction. ### Tavily + GPT-5 Accuracy: 58.1. Result ID: 699646735698665ec48a55f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Search API":"Tavily","LLM Backbone":"GPT-5"}. This record does not assert independent reproduction. ### Brave + GPT-5 Accuracy: 54.2. Result ID: 699646735698665ec48a55f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Search API":"Brave","LLM Backbone":"GPT-5"}. This record does not assert independent reproduction. ### Always Flawed Accuracy: 53.7. Result ID: 699646735698665ec48a55f9. [Reporting paper]() Recorded evaluation configuration: {"Type":"Baseline"}. This record does not assert independent reproduction. ### Random (50/50) Accuracy: 50. Result ID: 699646735698665ec48a55f7. [Reporting paper]() Recorded evaluation configuration: {"Type":"Baseline"}. This record does not assert independent reproduction. ### Always Not Flawed Accuracy: 46.3. Result ID: 699646735698665ec48a55f8. [Reporting paper]() Recorded evaluation configuration: {"Type":"Baseline"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.