# Information Retrieval on FinanceBench 150 samples Source: [Information Retrieval on FinanceBench 150 samples]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:41:14.455Z Evaluation of Information Retrieval performance using the 150-sample subset of the FinanceBench dataset, measured by document and page recall (DocRec@5, PageRec@5) and language generation metrics (Max BLEU@5, Max ROUGE-L@5). 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 | Information Retrieval | | Dataset (including any stated split) | FinanceBench 150 samples | | Metric | DocRec@5 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 11 of 11 | | 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 - [DocRec@5](): Higher is better; unit: PERCENT. - [PageRec@5](): Higher is better; unit: PERCENT. - [Max BLEU@5](): Higher is better; unit: PERCENT. - [Max ROUGE-L@5](): Higher is better; unit: PERCENT. ## Recorded results | Method | DocRec@5 | Result date | Report paper | | --- | --- | --- | --- | | Learned page scorer | 95 | Not recorded | 699bded809c33900fcd80310 | | BGE-M3 + Multi-HyDE + ReRanker | 93 | Not recorded | 699bded809c33900fcd80310 | | Dense baseline BGE-M3 | 88 | Not recorded | 699bded809c33900fcd80310 | | BGE-M3 + ReRanker | 87 | Not recorded | 699bded809c33900fcd80310 | | HyDE | 86 | Not recorded | 699bded809c33900fcd80310 | | Multi-HyDE | 85 | Not recorded | 699bded809c33900fcd80310 | | Query expansion | 68 | Not recorded | 699bded809c33900fcd80310 | | Hybrid fusion (BM25 + BGE-M3) | 61 | Not recorded | 699bded809c33900fcd80310 | | SPLADE | 50 | Not recorded | 699bded809c33900fcd80310 | | BM25 | 32 | Not recorded | 699bded809c33900fcd80310 | | Parent-Child | 31 | Not recorded | 699bded809c33900fcd80310 | ### Learned page scorer DocRec@5: 95. Result ID: 699d068f5698665ec4a6a95d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"k":"5"}. This record does not assert independent reproduction. ### BGE-M3 + Multi-HyDE + ReRanker DocRec@5: 93. Result ID: 699d068f5698665ec4a6a95c. [Reporting paper]() Recorded evaluation configuration: {"k":"5"}. This record does not assert independent reproduction. ### Dense baseline BGE-M3 DocRec@5: 88. Result ID: 699d068f5698665ec4a6a953. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"k":"5"}. This record does not assert independent reproduction. ### BGE-M3 + ReRanker DocRec@5: 87. Result ID: 699d068f5698665ec4a6a95b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"k":"5"}. This record does not assert independent reproduction. ### HyDE DocRec@5: 86. Result ID: 699d068f5698665ec4a6a959. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"k":"5"}. This record does not assert independent reproduction. ### Multi-HyDE DocRec@5: 85. Result ID: 699d068f5698665ec4a6a95a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"k":"5"}. This record does not assert independent reproduction. ### Query expansion DocRec@5: 68. Result ID: 699d068f5698665ec4a6a958. [Reporting paper]() Recorded evaluation configuration: {"k":"5"}. This record does not assert independent reproduction. ### Hybrid fusion (BM25 + BGE-M3) DocRec@5: 61. Result ID: 699d068f5698665ec4a6a956. [Reporting paper]() Recorded evaluation configuration: {"k":"5"}. This record does not assert independent reproduction. ### SPLADE DocRec@5: 50. Result ID: 699d068f5698665ec4a6a955. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"k":"5"}. This record does not assert independent reproduction. ### BM25 DocRec@5: 32. Result ID: 699d068f5698665ec4a6a954. [Reporting paper]() Recorded evaluation configuration: {"k":"5"}. This record does not assert independent reproduction. ### Parent-Child DocRec@5: 31. Result ID: 699d068f5698665ec4a6a957. [Reporting paper]() Recorded evaluation configuration: {"k":"5"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.