# Claim Verification on FinDVer mini (test) Source: [Claim Verification on FinDVer mini (test)]() Collection index: [llms.txt]() Data updated: 2026-04-21T09:57:49.884Z Evaluation of model performance on the test split of the FinDVer mini dataset for Claim Verification, reporting 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 | Claim Verification | | Dataset (including any stated split) | FinDVer mini (test) | | Metric | Accuracy | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Qwen-2.5 | 76 | Not recorded | 69e704cb7d0172140ec7efa0 | | MACE | 76 | Not recorded | 69e704cb7d0172140ec7efa0 | | Llama-3.1 | 75 | Not recorded | 69e704cb7d0172140ec7efa0 | | Mistral-Large | 75 | Not recorded | 69e704cb7d0172140ec7efa0 | | GPT-4o | 75 | Not recorded | 69e704cb7d0172140ec7efa0 | | MACE | 75 | Not recorded | 69e704cb7d0172140ec7efa0 | | Claude-3.5-Sonnet | 73 | Not recorded | 69e704cb7d0172140ec7efa0 | | Qwen-2.5 | 72 | Not recorded | 69e704cb7d0172140ec7efa0 | | Gemini-1.5-Pro | 71 | Not recorded | 69e704cb7d0172140ec7efa0 | | MACE | 68 | Not recorded | 69e704cb7d0172140ec7efa0 | | MACE | 64 | Not recorded | 69e704cb7d0172140ec7efa0 | | DeepSeek-V2-Lite | 60 | Not recorded | 69e704cb7d0172140ec7efa0 | ### Qwen-2.5 Accuracy: 76. Result ID: 69e74a0f47f34ce924ce019e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Parameters":"72B"}. This record does not assert independent reproduction. ### MACE Accuracy: 76. Result ID: 69e74a0f47f34ce924ce01a6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qw-235B","Components":"Pm + Em"}. This record does not assert independent reproduction. ### Llama-3.1 Accuracy: 75. Result ID: 69e74a0f47f34ce924ce019d. [Reporting paper]() Recorded evaluation configuration: {"Parameters":"70B"}. This record does not assert independent reproduction. ### Mistral-Large Accuracy: 75. Result ID: 69e74a0f47f34ce924ce019f. [Reporting paper]() Recorded evaluation configuration: {"Parameters":"123B"}. This record does not assert independent reproduction. ### GPT-4o Accuracy: 75. Result ID: 69e74a0f47f34ce924ce01a2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MACE Accuracy: 75. Result ID: 69e74a0f47f34ce924ce01a5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qw-72B","Components":"Pm + Em + Vm"}. This record does not assert independent reproduction. ### Claude-3.5-Sonnet Accuracy: 73. Result ID: 69e74a0f47f34ce924ce01a0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen-2.5 Accuracy: 72. Result ID: 69e74a0f47f34ce924ce019c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini-1.5-Pro Accuracy: 71. Result ID: 69e74a0f47f34ce924ce01a1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MACE Accuracy: 68. Result ID: 69e74a0f47f34ce924ce01a4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Ll-8B","Components":"Pm + Em + Vm'"}. This record does not assert independent reproduction. ### MACE Accuracy: 64. Result ID: 69e74a0f47f34ce924ce01a3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Mt-7B","Components":"Pm + Em + Vm'"}. This record does not assert independent reproduction. ### DeepSeek-V2-Lite Accuracy: 60. Result ID: 69e74a0f47f34ce924ce019b. [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.