# Repetition on Copyrighted Content without copyright notice 1.0 (test) Source: [Repetition on Copyrighted Content without copyright notice 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:00:31.386Z Evaluation of model performance on the Repetition task using the test split of the Copyrighted Content without copyright notice 1.0 dataset, measured using ROUGE and Refusal rate. 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 | Repetition | | Dataset (including any stated split) | Copyrighted Content without copyright notice 1.0 (test) | | Metric | ROUGE Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [ROUGE Score](): Higher is better; unit: PERCENT. - [Refusal Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | ROUGE Score | Result date | Report paper | | --- | --- | --- | --- | | Qwen2.5-VL\_7B | 94.12 | Not recorded | 69520adb53fdd5c36173d379 | | Qwen2.5-VL\_3B | 93.81 | Not recorded | 69520adb53fdd5c36173d379 | | GLM-4v\_9B | 91.3 | Not recorded | 69520adb53fdd5c36173d379 | | Claude-3.7 | 74.84 | Not recorded | 69520adb53fdd5c36173d379 | | LLaVA-NeXT\_13B | 69.34 | Not recorded | 69520adb53fdd5c36173d379 | | DeepSeek-VL\_7B | 61.28 | Not recorded | 69520adb53fdd5c36173d379 | | Janus-Pro\_7B | 53.8 | Not recorded | 69520adb53fdd5c36173d379 | | Gemini-2.0 | 48.88 | Not recorded | 69520adb53fdd5c36173d379 | | LLaVA-1.5\_13B | 42.52 | Not recorded | 69520adb53fdd5c36173d379 | | GPT-4o-mini | 42.07 | Not recorded | 69520adb53fdd5c36173d379 | | LLaVA-1.5\_7B | 41.07 | Not recorded | 69520adb53fdd5c36173d379 | | GPT-4o | 38.51 | Not recorded | 69520adb53fdd5c36173d379 | ### Qwen2.5-VL\_7B ROUGE Score: 94.12. Result ID: 6996af165698665ec4f94220. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL","Parameters":"7B"}. This record does not assert independent reproduction. ### Qwen2.5-VL\_3B ROUGE Score: 93.81. Result ID: 6996af165698665ec4f9421f. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL","Parameters":"3B"}. This record does not assert independent reproduction. ### GLM-4v\_9B ROUGE Score: 91.3. Result ID: 6996af165698665ec4f94222. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GLM-4v","Parameters":"9B"}. This record does not assert independent reproduction. ### Claude-3.7 ROUGE Score: 74.84. Result ID: 6996af165698665ec4f9421b. [Reporting paper]() Recorded evaluation configuration: {"Availability":"API-based"}. This record does not assert independent reproduction. ### LLaVA-NeXT\_13B ROUGE Score: 69.34. Result ID: 6996af165698665ec4f9421e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"LLaVA-NeXT","Parameters":"13B"}. This record does not assert independent reproduction. ### DeepSeek-VL\_7B ROUGE Score: 61.28. Result ID: 6996af165698665ec4f94221. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"DeepSeek-VL","Parameters":"7B"}. This record does not assert independent reproduction. ### Janus-Pro\_7B ROUGE Score: 53.8. Result ID: 6996af165698665ec4f94223. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Janus-Pro","Parameters":"7B"}. This record does not assert independent reproduction. ### Gemini-2.0 ROUGE Score: 48.88. Result ID: 6996af165698665ec4f9421a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Availability":"API-based"}. This record does not assert independent reproduction. ### LLaVA-1.5\_13B ROUGE Score: 42.52. Result ID: 6996af165698665ec4f9421d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"LLaVA-1.5","Parameters":"13B"}. This record does not assert independent reproduction. ### GPT-4o-mini ROUGE Score: 42.07. Result ID: 6996af165698665ec4f94218. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Availability":"API-based"}. This record does not assert independent reproduction. ### LLaVA-1.5\_7B ROUGE Score: 41.07. Result ID: 6996af165698665ec4f9421c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"LLaVA-1.5","Parameters":"7B"}. This record does not assert independent reproduction. ### GPT-4o ROUGE Score: 38.51. Result ID: 6996af165698665ec4f94219. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Availability":"API-based"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.