# Semantic Similarity on WIKI (test) Source: [Semantic Similarity on WIKI (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:37:18.623Z Evaluation of Semantic Similarity performance on the test split of the WIKI dataset, measured using metrics such as BLEU-4, rougeL, METEOR, and BertScore. 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 | Semantic Similarity | | Dataset (including any stated split) | WIKI (test) | | Metric | BLEU-4 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 - [BLEU-4](): Higher is better; unit: PERCENT. - [ROUGE-L](): Higher is better; unit: PERCENT. - [METEOR](): Higher is better; unit: PERCENT. - [BertScore (F1)](): Higher is better; unit: PERCENT. ## Recorded results | Method | BLEU-4 | Result date | Report paper | | --- | --- | --- | --- | | Llama3-8B-Instruct | 55.52 | Not recorded | 68fa78a61e209131cea799af | | Qwen2.5-7B-Instruct | 55 | Not recorded | 68fa78a61e209131cea799af | | Mistral-7B-Instruct | 54.96 | Not recorded | 68fa78a61e209131cea799af | | Qwen2.5-7B-Instruct | 53.57 | Not recorded | 68fa78a61e209131cea799af | | Mistral-7B-Instruct | 52.61 | Not recorded | 68fa78a61e209131cea799af | | Llama3-8B-Instruct | 52.09 | Not recorded | 68fa78a61e209131cea799af | | Qwen2.5-7B-Instruct | 51.84 | Not recorded | 68fa78a61e209131cea799af | | Mistral-7B-Instruct | 51.58 | Not recorded | 68fa78a61e209131cea799af | | Llama3-8B-Instruct | 48.99 | Not recorded | 68fa78a61e209131cea799af | | GPT-4o | 25.98 | Not recorded | 68fa78a61e209131cea799af | | Mistral-7B-Instruct | 21.25 | Not recorded | 68fa78a61e209131cea799af | | Qwen2.5-7B-Instruct | 20.21 | Not recorded | 68fa78a61e209131cea799af | | Llama3-8B-Instruct | 14.67 | Not recorded | 68fa78a61e209131cea799af | | GPT-4o | 13.25 | Not recorded | 68fa78a61e209131cea799af | | Mistral-7B-Instruct | 11.41 | Not recorded | 68fa78a61e209131cea799af | | Llama3-8B-Instruct | 9.39 | Not recorded | 68fa78a61e209131cea799af | | Qwen2.5-7B-Instruct | 7.33 | Not recorded | 68fa78a61e209131cea799af | ### Llama3-8B-Instruct BLEU-4: 55.52. Result ID: 699598913badfaffe693d0c9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"GETER"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct BLEU-4: 55. Result ID: 699598913badfaffe693d0ce. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"GETER"}. This record does not assert independent reproduction. ### Mistral-7B-Instruct BLEU-4: 54.96. Result ID: 699598913badfaffe693d0d3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"GETER"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct BLEU-4: 53.57. Result ID: 699598913badfaffe693d0cd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"LoRA"}. This record does not assert independent reproduction. ### Mistral-7B-Instruct BLEU-4: 52.61. Result ID: 699598913badfaffe693d0d2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"LoRA"}. This record does not assert independent reproduction. ### Llama3-8B-Instruct BLEU-4: 52.09. Result ID: 699598913badfaffe693d0c8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"LoRA"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct BLEU-4: 51.84. Result ID: 699598913badfaffe693d0cc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"LoRA w/o chains text"}. This record does not assert independent reproduction. ### Mistral-7B-Instruct BLEU-4: 51.58. Result ID: 699598913badfaffe693d0d1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"LoRA w/o chains text"}. This record does not assert independent reproduction. ### Llama3-8B-Instruct BLEU-4: 48.99. Result ID: 699598913badfaffe693d0c7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"LoRA w/o chains text"}. This record does not assert independent reproduction. ### GPT-4o BLEU-4: 25.98. Result ID: 699598913badfaffe693d0c4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"zero-shot"}. This record does not assert independent reproduction. ### Mistral-7B-Instruct BLEU-4: 21.25. Result ID: 699598913badfaffe693d0d0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"zero-shot"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct BLEU-4: 20.21. Result ID: 699598913badfaffe693d0cb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"zero-shot"}. This record does not assert independent reproduction. ### Llama3-8B-Instruct BLEU-4: 14.67. Result ID: 699598913badfaffe693d0c6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"zero-shot"}. This record does not assert independent reproduction. ### GPT-4o BLEU-4: 13.25. Result ID: 699598913badfaffe693d0c3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"zero-shot w/o chains text"}. This record does not assert independent reproduction. ### Mistral-7B-Instruct BLEU-4: 11.41. Result ID: 699598913badfaffe693d0cf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"zero-shot w/o chains text"}. This record does not assert independent reproduction. ### Llama3-8B-Instruct BLEU-4: 9.39. Result ID: 699598913badfaffe693d0c5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"zero-shot w/o chains text"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct BLEU-4: 7.33. Result ID: 699598913badfaffe693d0ca. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"zero-shot w/o chains text"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.