# Forgery Reasoning on TFR CTM Cross-Method Source: [Forgery Reasoning on TFR CTM Cross-Method]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:01:10.523Z Evaluation of model performance on the Forgery Reasoning task using the TFR CTM Cross-Method 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 CTM Cross-Method | | Metric | 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 - [Reasoning Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | Reasoning Score | Result date | Report paper | | --- | --- | --- | --- | | TextShield-R1 | 51.2 | Not recorded | 699d30aa6017c4460ffab609 | | SIDA\* | 36.3 | Not recorded | 699d30aa6017c4460ffab609 | | Qwen2.5-VL-7B | 36.2 | Not recorded | 699d30aa6017c4460ffab609 | | FakeShield\* | 36.2 | Not recorded | 699d30aa6017c4460ffab609 | | InternVL3-8B | 32.3 | Not recorded | 699d30aa6017c4460ffab609 | | MiniCPM\_V\_2.6 | 27.3 | Not recorded | 699d30aa6017c4460ffab609 | | InternVL3-2B | 25 | Not recorded | 699d30aa6017c4460ffab609 | | Qwen2.5-VL-3B | 24.6 | Not recorded | 699d30aa6017c4460ffab609 | | SIDA | 21.5 | Not recorded | 699d30aa6017c4460ffab609 | | FakeShield | 21.4 | Not recorded | 699d30aa6017c4460ffab609 | | GPT4o | 9.7 | Not recorded | 699d30aa6017c4460ffab609 | | InternVL3-8B | 8.8 | Not recorded | 699d30aa6017c4460ffab609 | | Qwen2.5-VL-3B | 5.6 | Not recorded | 699d30aa6017c4460ffab609 | | Qwen2.5-VL-7B | 4.5 | Not recorded | 699d30aa6017c4460ffab609 | | InternVL3-2B | 4 | Not recorded | 699d30aa6017c4460ffab609 | | MiniCPM\_V\_2.6 | 2.5 | Not recorded | 699d30aa6017c4460ffab609 | ### TextShield-R1 Reasoning Score: 51.2. Result ID: 699e56415698665ec4166344. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### SIDA\* Reasoning Score: 36.3. Result ID: 699e56415698665ec4166343. [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. ### Qwen2.5-VL-7B Reasoning Score: 36.2. Result ID: 699e56415698665ec416633f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### FakeShield\* Reasoning Score: 36.2. Result ID: 699e56415698665ec4166341. [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 Reasoning Score: 32.3. Result ID: 699e56415698665ec416633d. [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 Reasoning Score: 27.3. Result ID: 699e56415698665ec416633b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### InternVL3-2B Reasoning Score: 25. Result ID: 699e56415698665ec416633c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### Qwen2.5-VL-3B Reasoning Score: 24.6. Result ID: 699e56415698665ec416633e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### SIDA Reasoning Score: 21.5. Result ID: 699e56415698665ec4166342. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### FakeShield Reasoning Score: 21.4. Result ID: 699e56415698665ec4166340. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"Full training set images"}. This record does not assert independent reproduction. ### GPT4o Reasoning Score: 9.7. Result ID: 699e56415698665ec4166335. [Reporting paper]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. ### InternVL3-8B Reasoning Score: 8.8. Result ID: 699e56415698665ec4166338. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. ### Qwen2.5-VL-3B Reasoning Score: 5.6. Result ID: 699e56415698665ec4166339. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. ### Qwen2.5-VL-7B Reasoning Score: 4.5. Result ID: 699e56415698665ec416633a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. ### InternVL3-2B Reasoning Score: 4. Result ID: 699e56415698665ec4166337. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Fine-tuning":"None"}. This record does not assert independent reproduction. ### MiniCPM\_V\_2.6 Reasoning Score: 2.5. Result ID: 699e56415698665ec4166336. [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.