# Forgery Reasoning on TFR Cross-Language Source: [Forgery Reasoning on TFR Cross-Language]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:36:19.357Z Evaluation of model performance on the Forgery Reasoning task using the TFR Cross-Language dataset. 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 | Forgery Reasoning | | Dataset (including any stated split) | TFR Cross-Language | | Metric | Avg Reasoning Score | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [Avg Reasoning Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Avg Reasoning Score | Result date | Report paper | | --- | --- | --- | --- | | TextShield-R1 | 46.2 | Not recorded | 699d30aa6017c4460ffab609 | | Qwen2.5-VL-7B | 43.1 | Not recorded | 699d30aa6017c4460ffab609 | | SIDA\* | 43 | Not recorded | 699d30aa6017c4460ffab609 | | FakeShield\* | 42.9 | Not recorded | 699d30aa6017c4460ffab609 | | InternVL3-8B | 42 | Not recorded | 699d30aa6017c4460ffab609 | | MiniCPM\_V\_2.6 | 40.3 | Not recorded | 699d30aa6017c4460ffab609 | | Qwen2.5-VL-3B | 39.7 | Not recorded | 699d30aa6017c4460ffab609 | | InternVL3-2B | 39.5 | Not recorded | 699d30aa6017c4460ffab609 | | FakeShield | 34.8 | Not recorded | 699d30aa6017c4460ffab609 | | SIDA | 25 | Not recorded | 699d30aa6017c4460ffab609 | | InternVL3-8B | 18.1 | Not recorded | 699d30aa6017c4460ffab609 | | GPT4o | 14.2 | Not recorded | 699d30aa6017c4460ffab609 | | Qwen2.5-VL-7B | 10.4 | Not recorded | 699d30aa6017c4460ffab609 | | Qwen2.5-VL-3B | 7.9 | Not recorded | 699d30aa6017c4460ffab609 | | InternVL3-2B | 6.9 | Not recorded | 699d30aa6017c4460ffab609 | | MiniCPM\_V\_2.6 | 1.9 | Not recorded | 699d30aa6017c4460ffab609 | ### TextShield-R1 Avg Reasoning Score: 46.2. Result ID: 699e56415698665ec4166384. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Avg Reasoning Score: 43.1. Result ID: 699e56415698665ec416637f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### SIDA\* Avg Reasoning Score: 43. Result ID: 699e56415698665ec4166383. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images","Base MLLM":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### FakeShield\* Avg Reasoning Score: 42.9. Result ID: 699e56415698665ec4166381. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images","Base MLLM":"Qwen2.5-VL-7B"}. This record does not assert independent reproduction. ### InternVL3-8B Avg Reasoning Score: 42. Result ID: 699e56415698665ec416637d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### MiniCPM\_V\_2.6 Avg Reasoning Score: 40.3. Result ID: 699e56415698665ec416637b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### Qwen2.5-VL-3B Avg Reasoning Score: 39.7. Result ID: 699e56415698665ec416637e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### InternVL3-2B Avg Reasoning Score: 39.5. Result ID: 699e56415698665ec416637c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### FakeShield Avg Reasoning Score: 34.8. Result ID: 699e56415698665ec4166380. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### SIDA Avg Reasoning Score: 25. Result ID: 699e56415698665ec4166382. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### InternVL3-8B Avg Reasoning Score: 18.1. Result ID: 699e56415698665ec4166378. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. ### GPT4o Avg Reasoning Score: 14.2. Result ID: 699e56415698665ec4166375. [Reporting paper]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Avg Reasoning Score: 10.4. Result ID: 699e56415698665ec416637a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. ### Qwen2.5-VL-3B Avg Reasoning Score: 7.9. Result ID: 699e56415698665ec4166379. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. ### InternVL3-2B Avg Reasoning Score: 6.9. Result ID: 699e56415698665ec4166377. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. ### MiniCPM\_V\_2.6 Avg Reasoning Score: 1.9. Result ID: 699e56415698665ec4166376. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.