# Searching on HM3D Source: [Searching on HM3D]() Collection index: [llms.txt]() Data updated: 2026-03-04T20:09:33.279Z Evaluation of searching performance on the HM3D dataset, reporting SPL, SR, and RGTR metrics. 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 | Searching | | Dataset (including any stated split) | HM3D | | Metric | SPL | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 21 of 21 | | 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 - [SPL](): Higher is better; unit: PERCENT. - [SR](): Higher is better; unit: PERCENT. - [RGTR](): Higher is better; unit: PERCENT. ## Recorded results | Method | SPL | Result date | Report paper | | --- | --- | --- | --- | | SERP | 91 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SERP | 87 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SERP | 86.5 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SERP | 85.1 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SERP | 84.1 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SERP | 83 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SERP | 81.5 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SERP | 78.5 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SERP | 76 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SERP | 75.6 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SERP | 72.8 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SERP | 65.8 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SayPlan | 59.8 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SayPlan | 57.2 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SayPlan | 56.9 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SayPlan | 56.1 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SayPlan | 56 | Not recorded | 69a7bc7b2d603e6de3e3d415 | | SayPlan | 53.2 | Not recorded | 69a7bc7b2d603e6de3e3d415 | ### SERP SPL: 91. Result ID: 69a8917a6dbb7075b9513681. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-Max","Scenario":"00829"}. This record does not assert independent reproduction. ### SERP SPL: 87. Result ID: 69a8917a6dbb7075b9513680. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-Max","Scenario":"00824"}. This record does not assert independent reproduction. ### SERP SPL: 86.5. Result ID: 69a8917a6dbb7075b951367a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o","Scenario":"00829"}. This record does not assert independent reproduction. ### SERP SPL: 85.1. Result ID: 69a8917a6dbb7075b9513685. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-Max","Scenario":"00877"}. This record does not assert independent reproduction. ### SERP SPL: 84.1. Result ID: 69a8917a6dbb7075b9513682. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-Max","Scenario":"00843"}. This record does not assert independent reproduction. ### SERP SPL: 83. Result ID: 69a8917a6dbb7075b9513684. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-Max","Scenario":"00873"}. This record does not assert independent reproduction. ### SERP SPL: 81.5. Result ID: 69a8917a6dbb7075b9513679. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o","Scenario":"00824"}. This record does not assert independent reproduction. ### SERP SPL: 78.5. Result ID: 69a8917a6dbb7075b951367e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o","Scenario":"00877"}. This record does not assert independent reproduction. ### SERP SPL: 76. Result ID: 69a8917a6dbb7075b951367b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o","Scenario":"00843"}. This record does not assert independent reproduction. ### SERP SPL: 75.6. Result ID: 69a8917a6dbb7075b9513683. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-Max","Scenario":"00861"}. This record does not assert independent reproduction. ### SERP SPL: 72.8. Result ID: 69a8917a6dbb7075b951367d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o","Scenario":"00873"}. This record does not assert independent reproduction. ### SERP SPL: 65.8. Result ID: 69a8917a6dbb7075b951367c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o","Scenario":"00861"}. This record does not assert independent reproduction. ### SayPlan SPL: 59.8. Result ID: 69a8917a6dbb7075b9513676. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-Max","Scenario":"00873"}. This record does not assert independent reproduction. ### SayPlan SPL: 57.2. Result ID: 69a8917a6dbb7075b9513673. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-Max","Scenario":"00829"}. This record does not assert independent reproduction. ### SayPlan SPL: 56.9. Result ID: 69a8917a6dbb7075b9513677. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-Max","Scenario":"00877"}. This record does not assert independent reproduction. ### SayPlan SPL: 56.1. Result ID: 69a8917a6dbb7075b9513672. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-Max","Scenario":"00824"}. This record does not assert independent reproduction. ### SayPlan SPL: 56. Result ID: 69a8917a6dbb7075b9513674. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-Max","Scenario":"00843"}. This record does not assert independent reproduction. ### SayPlan SPL: 53.2. Result ID: 69a8917a6dbb7075b9513675. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-Max","Scenario":"00861"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.