# Embodied Question Answering on OpenEQA v1.0 (test) Source: [Embodied Question Answering on OpenEQA v1.0 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:48:09.569Z Evaluation of model performance on the test split of the OpenEQA v1.0 dataset for Embodied Question Answering, utilizing LLM-Match as a primary evaluation metric. 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 | Embodied Question Answering | | Dataset (including any stated split) | OpenEQA v1.0 (test) | | Metric | LLM-Match | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 32 of 32 | | 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 - [LLM-Match](): Higher is better; unit: PERCENT. - [Improvement](): Higher is better; unit: SCALAR. - [Scaling Improvement](): Higher is better; unit: SCALAR. ## Recorded results | Method | LLM-Match | Result date | Report paper | | --- | --- | --- | --- | | CoV | 67.7 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 67.64 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 67.33 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 67.23 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 67.2 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 67 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 66.3 | Not recorded | 69608b7853fdd5c36174444a | | Baseline | 62.4 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 59.82 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 59.77 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 59.39 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 59.23 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 59.16 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 59.07 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 59.03 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 59.03 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 58.82 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 58.8 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 58.75 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 58.15 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 57.15 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 57.1 | Not recorded | 69608b7853fdd5c36174444a | | Baseline | 52.65 | Not recorded | 69608b7853fdd5c36174444a | | Baseline | 52.3 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 51.62 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 51.56 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 51.41 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 50.8 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 50.15 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 49.85 | Not recorded | 69608b7853fdd5c36174444a | | CoV | 49.6 | Not recorded | 69608b7853fdd5c36174444a | | Baseline | 45.87 | Not recorded | 69608b7853fdd5c36174444a | ### CoV LLM-Match: 67.7. Result ID: 6997d6985698665ec42e934c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GLM-4.6v","Action Steps":6}. This record does not assert independent reproduction. ### CoV LLM-Match: 67.64. Result ID: 6997d6985698665ec42e934d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GLM-4.6v","Action Steps":7}. This record does not assert independent reproduction. ### CoV LLM-Match: 67.33. Result ID: 6997d6985698665ec42e9348. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GLM-4.6v","Action Steps":2}. This record does not assert independent reproduction. ### CoV LLM-Match: 67.23. Result ID: 6997d6985698665ec42e934b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GLM-4.6v","Action Steps":5}. This record does not assert independent reproduction. ### CoV LLM-Match: 67.2. Result ID: 6997d6985698665ec42e9349. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GLM-4.6v","Action Steps":3}. This record does not assert independent reproduction. ### CoV LLM-Match: 67. Result ID: 6997d6985698665ec42e9347. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GLM-4.6v","Action Steps":1}. This record does not assert independent reproduction. ### CoV LLM-Match: 66.3. Result ID: 6997d6985698665ec42e934a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GLM-4.6v","Action Steps":4}. This record does not assert independent reproduction. ### Baseline LLM-Match: 62.4. Result ID: 6997d6985698665ec42e9346. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GLM-4.6v"}. This record does not assert independent reproduction. ### CoV LLM-Match: 59.82. Result ID: 6997d6985698665ec42e9342. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-Flash","Action Steps":4}. This record does not assert independent reproduction. ### CoV LLM-Match: 59.77. Result ID: 6997d6985698665ec42e9345. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-Flash","Action Steps":7}. This record does not assert independent reproduction. ### CoV LLM-Match: 59.39. Result ID: 6997d6985698665ec42e9344. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-Flash","Action Steps":6}. This record does not assert independent reproduction. ### CoV LLM-Match: 59.23. Result ID: 6997d6985698665ec42e935c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Gemini-2.5-Flash","Action Steps":6}. This record does not assert independent reproduction. ### CoV LLM-Match: 59.16. Result ID: 6997d6985698665ec42e935d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Gemini-2.5-Flash","Action Steps":7}. This record does not assert independent reproduction. ### CoV LLM-Match: 59.07. Result ID: 6997d6985698665ec42e9340. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-Flash","Action Steps":2}. This record does not assert independent reproduction. ### CoV LLM-Match: 59.03. Result ID: 6997d6985698665ec42e9341. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-Flash","Action Steps":3}. This record does not assert independent reproduction. ### CoV LLM-Match: 59.03. Result ID: 6997d6985698665ec42e9343. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-Flash","Action Steps":5}. This record does not assert independent reproduction. ### CoV LLM-Match: 58.82. Result ID: 6997d6985698665ec42e935b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Gemini-2.5-Flash","Action Steps":5}. This record does not assert independent reproduction. ### CoV LLM-Match: 58.8. Result ID: 6997d6985698665ec42e9359. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Gemini-2.5-Flash","Action Steps":3}. This record does not assert independent reproduction. ### CoV LLM-Match: 58.75. Result ID: 6997d6985698665ec42e933f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-Flash","Action Steps":1}. This record does not assert independent reproduction. ### CoV LLM-Match: 58.15. Result ID: 6997d6985698665ec42e935a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Gemini-2.5-Flash","Action Steps":4}. This record does not assert independent reproduction. ### CoV LLM-Match: 57.15. Result ID: 6997d6985698665ec42e9358. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Gemini-2.5-Flash","Action Steps":2}. This record does not assert independent reproduction. ### CoV LLM-Match: 57.1. Result ID: 6997d6985698665ec42e9357. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Gemini-2.5-Flash","Action Steps":1}. This record does not assert independent reproduction. ### Baseline LLM-Match: 52.65. Result ID: 6997d6985698665ec42e933e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen3-VL-Flash"}. This record does not assert independent reproduction. ### Baseline LLM-Match: 52.3. Result ID: 6997d6985698665ec42e9356. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Gemini-2.5-Flash"}. This record does not assert independent reproduction. ### CoV LLM-Match: 51.62. Result ID: 6997d6985698665ec42e9355. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-4o-Mini","Action Steps":7}. This record does not assert independent reproduction. ### CoV LLM-Match: 51.56. Result ID: 6997d6985698665ec42e9353. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-4o-Mini","Action Steps":5}. This record does not assert independent reproduction. ### CoV LLM-Match: 51.41. Result ID: 6997d6985698665ec42e9354. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-4o-Mini","Action Steps":6}. This record does not assert independent reproduction. ### CoV LLM-Match: 50.8. Result ID: 6997d6985698665ec42e9352. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-4o-Mini","Action Steps":4}. This record does not assert independent reproduction. ### CoV LLM-Match: 50.15. Result ID: 6997d6985698665ec42e9350. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-4o-Mini","Action Steps":2}. This record does not assert independent reproduction. ### CoV LLM-Match: 49.85. Result ID: 6997d6985698665ec42e934f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-4o-Mini","Action Steps":1}. This record does not assert independent reproduction. ### CoV LLM-Match: 49.6. Result ID: 6997d6985698665ec42e9351. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"GPT-4o-Mini","Action Steps":3}. This record does not assert independent reproduction. ### Baseline LLM-Match: 45.87. Result ID: 6997d6985698665ec42e934e. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"GPT-4o-Mini"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.