# Fact Verification on TrendFact Source: [Fact Verification on TrendFact]() Collection index: [llms.txt]() Data updated: 2026-07-07T08:31:12.947Z Evaluation of model performance on the TrendFact dataset for Fact Verification, reporting F1, Precision, Recall, and 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 | Fact Verification | | Dataset (including any stated split) | TrendFact | | Metric | F1 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 - [F1 Score](): Higher is better; unit: PERCENT. - [Precision](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | FactISR | 61.17 | Not recorded | 68fa78b41e209131cea79de6 | | DeepSeek-R1-0528 | 58.89 | Not recorded | 68fa78b41e209131cea79de6 | | FactISR | 58.68 | Not recorded | 68fa78b41e209131cea79de6 | | QwQ-32B | 58.58 | Not recorded | 68fa78b41e209131cea79de6 | | Qwen3-32B | 58.14 | Not recorded | 68fa78b41e209131cea79de6 | | GPT-4.1 | 52.45 | Not recorded | 68fa78b41e209131cea79de6 | | DeepSeek-V3-0324 | 52.1 | Not recorded | 68fa78b41e209131cea79de6 | | Qwen3-32B | 50.06 | Not recorded | 68fa78b41e209131cea79de6 | | QwQ-32B-Preview | 49.52 | Not recorded | 68fa78b41e209131cea79de6 | | Qwen2.5-72B-instruct | 47.1 | Not recorded | 68fa78b41e209131cea79de6 | | CLAIMDECOMP | 42.53 | Not recorded | 68fa78b41e209131cea79de6 | | PROGRAM-FC | 40.46 | Not recorded | 68fa78b41e209131cea79de6 | ### FactISR F1 Score: 61.17. Result ID: 6a4cb93660b88bb339c88ee9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"QwQ-32B"}. This record does not assert independent reproduction. ### DeepSeek-R1-0528 F1 Score: 58.89. Result ID: 6a4cb93660b88bb339c88ee7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FactISR F1 Score: 58.68. Result ID: 6a4cb93660b88bb339c88ee8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Qwen3-32B"}. This record does not assert independent reproduction. ### QwQ-32B F1 Score: 58.58. Result ID: 6a4cb93660b88bb339c88ee6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-32B F1 Score: 58.14. Result ID: 6a4cb93660b88bb339c88ee5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"Think"}. This record does not assert independent reproduction. ### GPT-4.1 F1 Score: 52.45. Result ID: 6a4cb93660b88bb339c88ee4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DeepSeek-V3-0324 F1 Score: 52.1. Result ID: 6a4cb93660b88bb339c88ee3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-32B F1 Score: 50.06. Result ID: 6a4cb93660b88bb339c88ee2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Mode":"No think"}. This record does not assert independent reproduction. ### QwQ-32B-Preview F1 Score: 49.52. Result ID: 6a4cb93660b88bb339c88ee0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2.5-72B-instruct F1 Score: 47.1. Result ID: 6a4cb93660b88bb339c88ee1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### CLAIMDECOMP F1 Score: 42.53. Result ID: 6a4cb93660b88bb339c88edf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### PROGRAM-FC F1 Score: 40.46. Result ID: 6a4cb93660b88bb339c88ede. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.