# Source Prediction on Eval-Actions 1.0 (test) Source: [Source Prediction on Eval-Actions 1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:32:39.638Z Evaluation of Source Prediction performance on the test split of the Eval-Actions 1.0 dataset, measured using Accuracy, F1 Score, and AUC. 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 | Source Prediction | | Dataset (including any stated split) | Eval-Actions 1.0 (test) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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. - [AUC](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | AutoEval-S | 99.6 | Not recorded | 6978471ba2b28e761d87c9f6 | | QwenVL3-4B | 99.1 | Not recorded | 6978471ba2b28e761d87c9f6 | | AutoEval-S | 99.1 | Not recorded | 6978471ba2b28e761d87c9f6 | | QwenVL2.5-3B | 98.7 | Not recorded | 6978471ba2b28e761d87c9f6 | | QwenVL2.5-3B | 98.7 | Not recorded | 6978471ba2b28e761d87c9f6 | | InternVL3.5-4B | 98.7 | Not recorded | 6978471ba2b28e761d87c9f6 | | QwenVL3-4B | 96.8 | Not recorded | 6978471ba2b28e761d87c9f6 | | InternVL3.5-4B | 94.9 | Not recorded | 6978471ba2b28e761d87c9f6 | | AutoEval-P | 86.9 | Not recorded | 6978471ba2b28e761d87c9f6 | | QwenVL3-4B | 85.8 | Not recorded | 6978471ba2b28e761d87c9f6 | | InternVL3.5-4B | 85 | Not recorded | 6978471ba2b28e761d87c9f6 | | SmolVLM2.2B | 83.9 | Not recorded | 6978471ba2b28e761d87c9f6 | | QwenVL2.5-3B | 80.6 | Not recorded | 6978471ba2b28e761d87c9f6 | | SmolVLM2.2B | 76.5 | Not recorded | 6978471ba2b28e761d87c9f6 | | SmolVLM2.2B | 68.6 | Not recorded | 6978471ba2b28e761d87c9f6 | | InternVL3.5-4B | 46.6 | Not recorded | 6978471ba2b28e761d87c9f6 | | InternVL3.5-4B | 38.8 | Not recorded | 6978471ba2b28e761d87c9f6 | ### AutoEval-S Accuracy: 99.6. Result ID: 6999d1685698665ec44fe3b3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Rank-Guided (RG)"}. This record does not assert independent reproduction. ### QwenVL3-4B Accuracy: 99.1. Result ID: 6999d1685698665ec44fe3b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Rank-Guided (RG)"}. This record does not assert independent reproduction. ### AutoEval-S Accuracy: 99.1. Result ID: 6999d1685698665ec44fe3b2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Expert Grading (EG)"}. This record does not assert independent reproduction. ### QwenVL2.5-3B Accuracy: 98.7. Result ID: 6999d1685698665ec44fe3a9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Expert Grading (EG)"}. This record does not assert independent reproduction. ### QwenVL2.5-3B Accuracy: 98.7. Result ID: 6999d1685698665ec44fe3aa. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Rank-Guided (RG)"}. This record does not assert independent reproduction. ### InternVL3.5-4B Accuracy: 98.7. Result ID: 6999d1685698665ec44fe3ad. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Rank-Guided (RG)"}. This record does not assert independent reproduction. ### QwenVL3-4B Accuracy: 96.8. Result ID: 6999d1685698665ec44fe3af. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Expert Grading (EG)"}. This record does not assert independent reproduction. ### InternVL3.5-4B Accuracy: 94.9. Result ID: 6999d1685698665ec44fe3ac. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Expert Grading (EG)"}. This record does not assert independent reproduction. ### AutoEval-P Accuracy: 86.9. Result ID: 6999d1685698665ec44fe3b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Chain-of-Thought (CoT)"}. This record does not assert independent reproduction. ### QwenVL3-4B Accuracy: 85.8. Result ID: 6999d1685698665ec44fe3b1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Chain-of-Thought (CoT)"}. This record does not assert independent reproduction. ### InternVL3.5-4B Accuracy: 85. Result ID: 6999d1685698665ec44fe3ae. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Chain-of-Thought (CoT)"}. This record does not assert independent reproduction. ### SmolVLM2.2B Accuracy: 83.9. Result ID: 6999d1685698665ec44fe3a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Expert Grading (EG)"}. This record does not assert independent reproduction. ### QwenVL2.5-3B Accuracy: 80.6. Result ID: 6999d1685698665ec44fe3ab. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Chain-of-Thought (CoT)"}. This record does not assert independent reproduction. ### SmolVLM2.2B Accuracy: 76.5. Result ID: 6999d1685698665ec44fe3a7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Rank-Guided (RG)"}. This record does not assert independent reproduction. ### SmolVLM2.2B Accuracy: 68.6. Result ID: 6999d1685698665ec44fe3a8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Chain-of-Thought (CoT)"}. This record does not assert independent reproduction. ### InternVL3.5-4B Accuracy: 46.6. Result ID: 6999d1685698665ec44fe3a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Expert Grading (EG)","Supervised Fine-Tuning":"No (Zero-Shot)"}. This record does not assert independent reproduction. ### InternVL3.5-4B Accuracy: 38.8. Result ID: 6999d1685698665ec44fe3a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Evaluation Protocol":"Rank-Guided (RG)","Supervised Fine-Tuning":"No (Zero-Shot)"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.