# Target Generation on EZSTANCE Non-explicit (test) Source: [Target Generation on EZSTANCE Non-explicit (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:03:18.524Z Evaluation of Target Generation performance on the test split of the EZSTANCE Non-explicit dataset, using metrics like SS (SemSim), BTSD (%), and Human Evaluation (HE). 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 | Target Generation | | Dataset (including any stated split) | EZSTANCE Non-explicit (test) | | Metric | SS (SemSim) | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 16 of 16 | | 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 - [SS (SemSim)](): Higher is better; unit: SCALAR. - [BTSD (%)](): Lower is better; unit: PERCENT. - [Human Evaluation Score](): Higher is better; unit: SCALAR. ## Recorded results | Method | SS (SemSim) | Result date | Report paper | | --- | --- | --- | --- | | GPT-3.5 | 0.85 | Not recorded | 68fa78f21e209131cea7b5e1 | | Llama-3-8B | 0.84 | Not recorded | 68fa78f21e209131cea7b5e1 | | Llama-3-70B | 0.84 | Not recorded | 68fa78f21e209131cea7b5e1 | | Mistral-large | 0.84 | Not recorded | 68fa78f21e209131cea7b5e1 | | GPT-4o | 0.83 | Not recorded | 68fa78f21e209131cea7b5e1 | | Gemini-flash | 0.83 | Not recorded | 68fa78f21e209131cea7b5e1 | | Llama-3-70B | 0.83 | Not recorded | 68fa78f21e209131cea7b5e1 | | Gemini-pro | 0.82 | Not recorded | 68fa78f21e209131cea7b5e1 | | Llama-3-8B | 0.82 | Not recorded | 68fa78f21e209131cea7b5e1 | | Mistral-large | 0.82 | Not recorded | 68fa78f21e209131cea7b5e1 | | Gemini-flash | 0.81 | Not recorded | 68fa78f21e209131cea7b5e1 | | Mistral-small | 0.81 | Not recorded | 68fa78f21e209131cea7b5e1 | | GPT-4o | 0.8 | Not recorded | 68fa78f21e209131cea7b5e1 | | Gemini-pro | 0.8 | Not recorded | 68fa78f21e209131cea7b5e1 | | Mistral-small | 0.8 | Not recorded | 68fa78f21e209131cea7b5e1 | | GPT-3.5 | 0.79 | Not recorded | 68fa78f21e209131cea7b5e1 | ### GPT-3.5 SS (SemSim): 0.85. Result ID: 6995b1ed3badfaffe6b1a8ab. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG&SD"}. This record does not assert independent reproduction. ### Llama-3-8B SS (SemSim): 0.84. Result ID: 6995b1ed3badfaffe6b1a8b3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG&SD"}. This record does not assert independent reproduction. ### Llama-3-70B SS (SemSim): 0.84. Result ID: 6995b1ed3badfaffe6b1a8b5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG&SD"}. This record does not assert independent reproduction. ### Mistral-large SS (SemSim): 0.84. Result ID: 6995b1ed3badfaffe6b1a8b9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG&SD"}. This record does not assert independent reproduction. ### GPT-4o SS (SemSim): 0.83. Result ID: 6995b1ed3badfaffe6b1a8ad. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG&SD"}. This record does not assert independent reproduction. ### Gemini-flash SS (SemSim): 0.83. Result ID: 6995b1ed3badfaffe6b1a8af. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG&SD"}. This record does not assert independent reproduction. ### Llama-3-70B SS (SemSim): 0.83. Result ID: 6995b1ed3badfaffe6b1a8b4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG+SD"}. This record does not assert independent reproduction. ### Gemini-pro SS (SemSim): 0.82. Result ID: 6995b1ed3badfaffe6b1a8b1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG&SD"}. This record does not assert independent reproduction. ### Llama-3-8B SS (SemSim): 0.82. Result ID: 6995b1ed3badfaffe6b1a8b2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG+SD"}. This record does not assert independent reproduction. ### Mistral-large SS (SemSim): 0.82. Result ID: 6995b1ed3badfaffe6b1a8b8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG+SD"}. This record does not assert independent reproduction. ### Gemini-flash SS (SemSim): 0.81. Result ID: 6995b1ed3badfaffe6b1a8ae. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG+SD"}. This record does not assert independent reproduction. ### Mistral-small SS (SemSim): 0.81. Result ID: 6995b1ed3badfaffe6b1a8b7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG&SD"}. This record does not assert independent reproduction. ### GPT-4o SS (SemSim): 0.8. Result ID: 6995b1ed3badfaffe6b1a8ac. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG+SD"}. This record does not assert independent reproduction. ### Gemini-pro SS (SemSim): 0.8. Result ID: 6995b1ed3badfaffe6b1a8b0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG+SD"}. This record does not assert independent reproduction. ### Mistral-small SS (SemSim): 0.8. Result ID: 6995b1ed3badfaffe6b1a8b6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG+SD"}. This record does not assert independent reproduction. ### GPT-3.5 SS (SemSim): 0.79. Result ID: 6995b1ed3badfaffe6b1a8aa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG+SD"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.