# Multi-turn financial advisory dialogue on Conv-FinRe (10 users x 23 steps each) Source: [Multi-turn financial advisory dialogue on Conv-FinRe (10 users x 23 steps each)]() Collection index: [llms.txt]() Data updated: 2026-03-16T09:41:57.051Z Evaluation of model performance on the Conv-FinRe dataset, focusing on multi-turn financial advisory dialogue capabilities, measured using NDCG, UPR, D\_bar, SVR\_s, Sev. SVR, and MDR. 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 | Multi-turn financial advisory dialogue | | Dataset (including any stated split) | Conv-FinRe (10 users x 23 steps each) | | Metric | NDCG | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 7 of 7 | | 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 - [NDCG](): Higher is better; unit: SCALAR. - [UPR](): Higher is better; unit: SCALAR. - [D\_bar](): Higher is better; unit: SCALAR. - [SVR\_s](): Higher is better; unit: SCALAR. - [Sev. SVR](): Higher is better; unit: SCALAR. - [MDR](): Lower is better; unit: PERCENT. ## Recorded results | Method | NDCG | Result date | Report paper | | --- | --- | --- | --- | | Claude Sonnet 4.6 | 0.744 | Not recorded | 69b78e560636e5bf4afbd9e8 | | GPT-5.2 | 0.728 | Not recorded | 69b78e560636e5bf4afbd9e8 | | Qwen3-32B | 0.692 | Not recorded | 69b78e560636e5bf4afbd9e8 | | Mistral Large 3 | 0.691 | Not recorded | 69b78e560636e5bf4afbd9e8 | | Ministral 3 14B | 0.656 | Not recorded | 69b78e560636e5bf4afbd9e8 | | Qwen2.5-7B | 0.654 | Not recorded | 69b78e560636e5bf4afbd9e8 | | Gemma 3 12B-IT | 0.651 | Not recorded | 69b78e560636e5bf4afbd9e8 | ### Claude Sonnet 4.6 NDCG: 0.744. Result ID: 69b7d06247f34ce9249fe37b. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-5.2 NDCG: 0.728. Result ID: 69b7d06247f34ce9249fe37a. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-32B NDCG: 0.692. Result ID: 69b7d06247f34ce9249fe377. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Mistral Large 3 NDCG: 0.691. Result ID: 69b7d06247f34ce9249fe37d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Ministral 3 14B NDCG: 0.656. Result ID: 69b7d06247f34ce9249fe37c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen2.5-7B NDCG: 0.654. Result ID: 69b7d06247f34ce9249fe378. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemma 3 12B-IT NDCG: 0.651. Result ID: 69b7d06247f34ce9249fe379. [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.