# Open-style Response Generation on Open-LLM Leaderboard Source: [Open-style Response Generation on Open-LLM Leaderboard]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:30:34.386Z Evaluation of open-ended response generation capabilities using the Open-LLM Leaderboard framework, measured by the Accuracy 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 | Open-style response generation | | Dataset (including any stated split) | Open-LLM Leaderboard | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 28 of 28 | | 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 - [Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy | Result date | Report paper | | --- | --- | --- | --- | | DRAG\_E | 53.45 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_C | 53.19 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_C | 52.66 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_E | 52.36 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_C | 51.73 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_E | 50.26 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_G | 49.13 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_G | 49.12 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_G | 48.73 | Not recorded | 68fa79031e209131cea7baa6 | | Gemma-2-9b-it | 46.44 | Not recorded | 68fa79031e209131cea7baa6 | | Llama-3.1-8B-Instruct | 45.07 | Not recorded | 68fa79031e209131cea7baa6 | | Qwen2.5-7B-Instruct | 44.67 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_E | 40.13 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_C | 39.84 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_G | 38.22 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_C | 37.5 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_E | 37.31 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_C | 37.26 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_E | 37.23 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_G | 36.01 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_G | 35.98 | Not recorded | 68fa79031e209131cea7baa6 | | Phi-3.5-mini-instruct | 35.26 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_E | 34.12 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_C | 33.65 | Not recorded | 68fa79031e209131cea7baa6 | | DRAG\_G | 32.79 | Not recorded | 68fa79031e209131cea7baa6 | | Qwen2.5-3B-Instruct | 32.59 | Not recorded | 68fa79031e209131cea7baa6 | | Gemma-2-2b-it | 32.54 | Not recorded | 68fa79031e209131cea7baa6 | | Llama-3.2-3B-Instruct | 29.85 | Not recorded | 68fa79031e209131cea7baa6 | ### DRAG\_E Accuracy: 53.45. Result ID: 6995b7053badfaffe6b7bb95. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Gemma-2-9b-it","Distillation":"Evidence-based"}. This record does not assert independent reproduction. ### DRAG\_C Accuracy: 53.19. Result ID: 6995b7053badfaffe6b7bb96. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Gemma-2-9b-it","Distillation":"Combined"}. This record does not assert independent reproduction. ### DRAG\_C Accuracy: 52.66. Result ID: 6995b7053badfaffe6b7bb92. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct","Distillation":"Combined"}. This record does not assert independent reproduction. ### DRAG\_E Accuracy: 52.36. Result ID: 6995b7053badfaffe6b7bb91. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct","Distillation":"Evidence-based"}. This record does not assert independent reproduction. ### DRAG\_C Accuracy: 51.73. Result ID: 6995b7053badfaffe6b7bb8e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct","Distillation":"Combined"}. This record does not assert independent reproduction. ### DRAG\_E Accuracy: 50.26. Result ID: 6995b7053badfaffe6b7bb8d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct","Distillation":"Evidence-based"}. This record does not assert independent reproduction. ### DRAG\_G Accuracy: 49.13. Result ID: 6995b7053badfaffe6b7bb8c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama-3.1-8B-Instruct","Distillation":"Graph-based"}. This record does not assert independent reproduction. ### DRAG\_G Accuracy: 49.12. Result ID: 6995b7053badfaffe6b7bb94. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Gemma-2-9b-it","Distillation":"Graph-based"}. This record does not assert independent reproduction. ### DRAG\_G Accuracy: 48.73. Result ID: 6995b7053badfaffe6b7bb90. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct","Distillation":"Graph-based"}. This record does not assert independent reproduction. ### Gemma-2-9b-it Accuracy: 46.44. Result ID: 6995b7053badfaffe6b7bb93. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distillation":"None"}. This record does not assert independent reproduction. ### Llama-3.1-8B-Instruct Accuracy: 45.07. Result ID: 6995b7053badfaffe6b7bb8b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Distillation":"None"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Accuracy: 44.67. Result ID: 6995b7053badfaffe6b7bb8f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Distillation":"None"}. This record does not assert independent reproduction. ### DRAG\_E Accuracy: 40.13. Result ID: 6995b7053badfaffe6b7bb81. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Phi-3.5-mini-instruct","Distillation":"Evidence-based"}. This record does not assert independent reproduction. ### DRAG\_C Accuracy: 39.84. Result ID: 6995b7053badfaffe6b7bb82. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Phi-3.5-mini-instruct","Distillation":"Combined"}. This record does not assert independent reproduction. ### DRAG\_G Accuracy: 38.22. Result ID: 6995b7053badfaffe6b7bb80. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Phi-3.5-mini-instruct","Distillation":"Graph-based"}. This record does not assert independent reproduction. ### DRAG\_C Accuracy: 37.5. Result ID: 6995b7053badfaffe6b7bb86. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct","Distillation":"Combined"}. This record does not assert independent reproduction. ### DRAG\_E Accuracy: 37.31. Result ID: 6995b7053badfaffe6b7bb99. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Gemma-2-2b-it","Distillation":"Evidence-based"}. This record does not assert independent reproduction. ### DRAG\_C Accuracy: 37.26. Result ID: 6995b7053badfaffe6b7bb9a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Gemma-2-2b-it","Distillation":"Combined"}. This record does not assert independent reproduction. ### DRAG\_E Accuracy: 37.23. Result ID: 6995b7053badfaffe6b7bb85. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct","Distillation":"Evidence-based"}. This record does not assert independent reproduction. ### DRAG\_G Accuracy: 36.01. Result ID: 6995b7053badfaffe6b7bb84. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-3B-Instruct","Distillation":"Graph-based"}. This record does not assert independent reproduction. ### DRAG\_G Accuracy: 35.98. Result ID: 6995b7053badfaffe6b7bb98. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Gemma-2-2b-it","Distillation":"Graph-based"}. This record does not assert independent reproduction. ### Phi-3.5-mini-instruct Accuracy: 35.26. Result ID: 6995b7053badfaffe6b7bb7f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Distillation":"None"}. This record does not assert independent reproduction. ### DRAG\_E Accuracy: 34.12. Result ID: 6995b7053badfaffe6b7bb89. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama-3.2-3B-Instruct","Distillation":"Evidence-based"}. This record does not assert independent reproduction. ### DRAG\_C Accuracy: 33.65. Result ID: 6995b7053badfaffe6b7bb8a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama-3.2-3B-Instruct","Distillation":"Combined"}. This record does not assert independent reproduction. ### DRAG\_G Accuracy: 32.79. Result ID: 6995b7053badfaffe6b7bb88. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama-3.2-3B-Instruct","Distillation":"Graph-based"}. This record does not assert independent reproduction. ### Qwen2.5-3B-Instruct Accuracy: 32.59. Result ID: 6995b7053badfaffe6b7bb83. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Distillation":"None"}. This record does not assert independent reproduction. ### Gemma-2-2b-it Accuracy: 32.54. Result ID: 6995b7053badfaffe6b7bb97. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Distillation":"None"}. This record does not assert independent reproduction. ### Llama-3.2-3B-Instruct Accuracy: 29.85. Result ID: 6995b7053badfaffe6b7bb87. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Distillation":"None"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.