# Free-form answer generation on KLAR (train) Source: [Free-form answer generation on KLAR (train)]() Collection index: [llms.txt]() Data updated: 2026-06-08T06:32:02.765Z Evaluation of model performance on the KLAR dataset (train split) for the task of free-form answer generation, measured using Accuracy. 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 | Free-form answer generation | | Dataset (including any stated split) | KLAR (train) | | Metric | Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 | | --- | --- | --- | --- | | GRPO | 49.69 | Not recorded | 6a264c8590966ade919be956 | | Baseline | 47.68 | Not recorded | 6a264c8590966ade919be956 | | CPT + GRPO | 45.97 | Not recorded | 6a264c8590966ade919be956 | | CPT + SFT | 45.43 | Not recorded | 6a264c8590966ade919be956 | | SFT | 43.23 | Not recorded | 6a264c8590966ade919be956 | | CPT | 38.99 | Not recorded | 6a264c8590966ade919be956 | | CPT + GRPO | 29.8 | Not recorded | 6a264c8590966ade919be956 | | GRPO | 29 | Not recorded | 6a264c8590966ade919be956 | | Baseline | 24.6 | Not recorded | 6a264c8590966ade919be956 | | CPT + SFT | 20.7 | Not recorded | 6a264c8590966ade919be956 | | SFT | 18.1 | Not recorded | 6a264c8590966ade919be956 | | CPT | 17 | Not recorded | 6a264c8590966ade919be956 | ### GRPO Accuracy: 49.69. Result ID: 6a266179fbc373592c226c4e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### Baseline Accuracy: 47.68. Result ID: 6a266179fbc373592c226c4a. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### CPT + GRPO Accuracy: 45.97. Result ID: 6a266179fbc373592c226c4f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### CPT + SFT Accuracy: 45.43. Result ID: 6a266179fbc373592c226c4d. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### SFT Accuracy: 43.23. Result ID: 6a266179fbc373592c226c4c. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### CPT Accuracy: 38.99. Result ID: 6a266179fbc373592c226c4b. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction. ### CPT + GRPO Accuracy: 29.8. Result ID: 6a266179fbc373592c226c49. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction. ### GRPO Accuracy: 29. Result ID: 6a266179fbc373592c226c48. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction. ### Baseline Accuracy: 24.6. Result ID: 6a266179fbc373592c226c44. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction. ### CPT + SFT Accuracy: 20.7. Result ID: 6a266179fbc373592c226c47. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction. ### SFT Accuracy: 18.1. Result ID: 6a266179fbc373592c226c46. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction. ### CPT Accuracy: 17. Result ID: 6a266179fbc373592c226c45. [Reporting paper]() Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.