# Financial Compliance Classification on FinGuard-Bench query-level Source: [Financial Compliance Classification on FinGuard-Bench query-level]() Collection index: [llms.txt]() Data updated: 2026-05-29T08:53:09.636Z Evaluation of model performance on financial compliance classification tasks using the query-level subset of the FinGuard-Bench dataset, measured by F1 score. 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 | Financial Compliance Classification | | Dataset (including any stated split) | FinGuard-Bench query-level | | 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. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | FinGuard | 90.23 | Not recorded | 6a191d76dbd7150506f826e5 | | FinGuard | 84.13 | Not recorded | 6a191d76dbd7150506f826e5 | | Qwen3.5-397B-A17B | 78.68 | Not recorded | 6a191d76dbd7150506f826e5 | | GPT-5.1 | 74.26 | Not recorded | 6a191d76dbd7150506f826e5 | | Gemini-3.1-Flash | 61.28 | Not recorded | 6a191d76dbd7150506f826e5 | | PolyGuard-Qwen-7B | 52.46 | Not recorded | 6a191d76dbd7150506f826e5 | | Qwen3Guard-Gen-8B | 35.5 | Not recorded | 6a191d76dbd7150506f826e5 | | Qwen3.5-9B | 33.63 | Not recorded | 6a191d76dbd7150506f826e5 | | LlamaGuard3-8B | 23.94 | Not recorded | 6a191d76dbd7150506f826e5 | | NemoGuard-8B | 16.97 | Not recorded | 6a191d76dbd7150506f826e5 | | Qwen3-8B | 16.69 | Not recorded | 6a191d76dbd7150506f826e5 | | Qwen3Guard-Gen-8B | 11.16 | Not recorded | 6a191d76dbd7150506f826e5 | ### FinGuard F1 Score: 90.23. Result ID: 6a195282fbc373592c13c445. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"self-play":"true"}. This record does not assert independent reproduction. ### FinGuard F1 Score: 84.13. Result ID: 6a195282fbc373592c13c444. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"self-play":"false"}. This record does not assert independent reproduction. ### Qwen3.5-397B-A17B F1 Score: 78.68. Result ID: 6a195282fbc373592c13c43c. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-5.1 F1 Score: 74.26. Result ID: 6a195282fbc373592c13c43e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini-3.1-Flash F1 Score: 61.28. Result ID: 6a195282fbc373592c13c43d. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### PolyGuard-Qwen-7B F1 Score: 52.46. Result ID: 6a195282fbc373592c13c441. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3Guard-Gen-8B F1 Score: 35.5. Result ID: 6a195282fbc373592c13c442. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"strict"}. This record does not assert independent reproduction. ### Qwen3.5-9B F1 Score: 33.63. Result ID: 6a195282fbc373592c13c43b. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LlamaGuard3-8B F1 Score: 23.94. Result ID: 6a195282fbc373592c13c43f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### NemoGuard-8B F1 Score: 16.97. Result ID: 6a195282fbc373592c13c440. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-8B F1 Score: 16.69. Result ID: 6a195282fbc373592c13c43a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3Guard-Gen-8B F1 Score: 11.16. Result ID: 6a195282fbc373592c13c443. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"loose"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.