# Paraphrasing Robustness on ELI5 prompts 32-bit payload Llama3.1-8B (test) Source: [Paraphrasing Robustness on ELI5 prompts 32-bit payload Llama3.1-8B (test)]() Collection index: [llms.txt]() Data updated: 2026-05-13T09:14:07.889Z Evaluation of model robustness against paraphrasing perturbations applied to the ELI5 32-bit payload test set generated by Llama3.1-8B. Performance is measured using Bit Accuracy. 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 | Paraphrasing Robustness | | Dataset (including any stated split) | ELI5 prompts 32-bit payload Llama3.1-8B (test) | | Metric | Bit Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 - [Bit Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Bit Accuracy | Result date | Report paper | | --- | --- | --- | --- | | MC2Mark | 50.9 | Not recorded | 6a0405c4dbc836b87d8277a1 | | Ours+ | 50.9 | Not recorded | 6a0405c4dbc836b87d8277a1 | | StealthInk | 50.7 | Not recorded | 6a0405c4dbc836b87d8277a1 | | MPAC | 50.5 | Not recorded | 6a0405c4dbc836b87d8277a1 | | BiMark | 50.4 | Not recorded | 6a0405c4dbc836b87d8277a1 | | RSBH | 50.1 | Not recorded | 6a0405c4dbc836b87d8277a1 | | MirrorMark | 49.8 | Not recorded | 6a0405c4dbc836b87d8277a1 | ### MC2Mark Bit Accuracy: 50.9. Result ID: 6a04400d47f34ce924ea53ee. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Paraphraser":"GPT-5-MINI","Payload":"32-bit"}. This record does not assert independent reproduction. ### Ours+ Bit Accuracy: 50.9. Result ID: 6a04400d47f34ce924ea53f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Paraphraser":"GPT-5-MINI","Payload":"32-bit","Type":"Stateful Encoder"}. This record does not assert independent reproduction. ### StealthInk Bit Accuracy: 50.7. Result ID: 6a04400d47f34ce924ea53f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Paraphraser":"GPT-5-MINI","Payload":"32-bit"}. This record does not assert independent reproduction. ### MPAC Bit Accuracy: 50.5. Result ID: 6a04400d47f34ce924ea53ef. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Paraphraser":"GPT-5-MINI","Payload":"32-bit"}. This record does not assert independent reproduction. ### BiMark Bit Accuracy: 50.4. Result ID: 6a04400d47f34ce924ea53ed. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Paraphraser":"GPT-5-MINI","Payload":"32-bit"}. This record does not assert independent reproduction. ### RSBH Bit Accuracy: 50.1. Result ID: 6a04400d47f34ce924ea53f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Paraphraser":"GPT-5-MINI","Payload":"32-bit"}. This record does not assert independent reproduction. ### MirrorMark Bit Accuracy: 49.8. Result ID: 6a04400d47f34ce924ea53f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Paraphraser":"GPT-5-MINI","Payload":"32-bit"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.