# Short-context Reading Comprehension on DROP (F1, ROUGE-L) Source: [Short-context Reading Comprehension on DROP (F1, ROUGE-L)]() Collection index: [llms.txt]() Data updated: 2026-06-11T11:37:01.968Z Evaluation of short-context reading comprehension performance on the DROP dataset, reporting F1 score and ROUGE-L 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 | Short-context Reading Comprehension | | Dataset (including any stated split) | DROP | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 - [F1 Score](): Higher is better; unit: PERCENT. - [ROUGE-L Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | Base+ctx | 45.18 | Not recorded | 6a2a4157d33dfb23e78395df | | Base+ctx | 42.61 | Not recorded | 6a2a4157d33dfb23e78395df | | D2Latom | 30.66 | Not recorded | 6a2a4157d33dfb23e78395df | | D2Lckpt | 29.62 | Not recorded | 6a2a4157d33dfb23e78395df | | D2Latom | 29.52 | Not recorded | 6a2a4157d33dfb23e78395df | | Doc2Atom | 28.31 | Not recorded | 6a2a4157d33dfb23e78395df | | D2Lraw | 27.12 | Not recorded | 6a2a4157d33dfb23e78395df | | Doc2Atom | 27.05 | Not recorded | 6a2a4157d33dfb23e78395df | | D2Lraw | 26.98 | Not recorded | 6a2a4157d33dfb23e78395df | | D2Lckpt | 10.07 | Not recorded | 6a2a4157d33dfb23e78395df | ### Base+ctx F1 Score: 45.18. Result ID: 6a2a9cbefbc373592c28e5c3. [Reporting paper]() Recorded evaluation configuration: {"LLM Backbone":"Qwen3-4B-Instruct","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### Base+ctx F1 Score: 42.61. Result ID: 6a2a9cbefbc373592c28e5be. [Reporting paper]() Recorded evaluation configuration: {"LLM Backbone":"Gemma-2-2B-It","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### D2Latom F1 Score: 30.66. Result ID: 6a2a9cbefbc373592c28e5c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM Backbone":"Qwen3-4B-Instruct","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### D2Lckpt F1 Score: 29.62. Result ID: 6a2a9cbefbc373592c28e5bf. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM Backbone":"Gemma-2-2B-It","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### D2Latom F1 Score: 29.52. Result ID: 6a2a9cbefbc373592c28e5c1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM Backbone":"Gemma-2-2B-It","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### Doc2Atom F1 Score: 28.31. Result ID: 6a2a9cbefbc373592c28e5c2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM Backbone":"Gemma-2-2B-It","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### D2Lraw F1 Score: 27.12. Result ID: 6a2a9cbefbc373592c28e5c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM Backbone":"Qwen3-4B-Instruct","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### Doc2Atom F1 Score: 27.05. Result ID: 6a2a9cbefbc373592c28e5c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM Backbone":"Qwen3-4B-Instruct","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### D2Lraw F1 Score: 26.98. Result ID: 6a2a9cbefbc373592c28e5c0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM Backbone":"Gemma-2-2B-It","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. ### D2Lckpt F1 Score: 10.07. Result ID: 6a2a9cbefbc373592c28e5c4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"LLM Backbone":"Qwen3-4B-Instruct","Evaluation Protocol":"In-domain"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.