# Stance Detection on EZSTANCE Non-explicit (test) Source: [Stance Detection on EZSTANCE Non-explicit (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T06:02:48.299Z Evaluation of Stance Detection performance on the test split of the EZSTANCE Non-explicit dataset, reporting SC (%). 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 | Stance Detection | | Dataset (including any stated split) | EZSTANCE Non-explicit (test) | | Metric | SC (%) | | Unit | PERCENT | | 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 - [SC (%)](): Higher is better; unit: PERCENT. ## Recorded results | Method | SC (%) | Result date | Report paper | | --- | --- | --- | --- | | Gemini-pro | 48.53 | Not recorded | 68fa78f21e209131cea7b5e1 | | Llama-3-8B | 47.98 | Not recorded | 68fa78f21e209131cea7b5e1 | | Llama-3-70B | 46.57 | Not recorded | 68fa78f21e209131cea7b5e1 | | Mistral-large | 46.55 | Not recorded | 68fa78f21e209131cea7b5e1 | | GPT-3.5 | 45.8 | Not recorded | 68fa78f21e209131cea7b5e1 | | Llama-3-70B | 45.7 | Not recorded | 68fa78f21e209131cea7b5e1 | | GPT-3.5 | 45.54 | Not recorded | 68fa78f21e209131cea7b5e1 | | Llama-3-8B | 45.48 | Not recorded | 68fa78f21e209131cea7b5e1 | | Gemini-flash | 45.15 | Not recorded | 68fa78f21e209131cea7b5e1 | | Gemini-flash | 44.87 | Not recorded | 68fa78f21e209131cea7b5e1 | | GPT-4o | 43.84 | Not recorded | 68fa78f21e209131cea7b5e1 | | Mistral-small | 43.34 | Not recorded | 68fa78f21e209131cea7b5e1 | | Mistral-large | 43.15 | Not recorded | 68fa78f21e209131cea7b5e1 | | Mistral-small | 41.87 | Not recorded | 68fa78f21e209131cea7b5e1 | | Gemini-pro | 41.39 | Not recorded | 68fa78f21e209131cea7b5e1 | | GPT-4o | 39.92 | Not recorded | 68fa78f21e209131cea7b5e1 | ### Gemini-pro SC (%): 48.53. Result ID: 6995b1ed3badfaffe6b1a8c1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG&SD"}. This record does not assert independent reproduction. ### Llama-3-8B SC (%): 47.98. Result ID: 6995b1ed3badfaffe6b1a8c2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG+SD"}. This record does not assert independent reproduction. ### Llama-3-70B SC (%): 46.57. Result ID: 6995b1ed3badfaffe6b1a8c5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG&SD"}. This record does not assert independent reproduction. ### Mistral-large SC (%): 46.55. Result ID: 6995b1ed3badfaffe6b1a8c9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG&SD"}. This record does not assert independent reproduction. ### GPT-3.5 SC (%): 45.8. Result ID: 6995b1ed3badfaffe6b1a8bb. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG&SD"}. This record does not assert independent reproduction. ### Llama-3-70B SC (%): 45.7. Result ID: 6995b1ed3badfaffe6b1a8c4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG+SD"}. This record does not assert independent reproduction. ### GPT-3.5 SC (%): 45.54. Result ID: 6995b1ed3badfaffe6b1a8ba. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG+SD"}. This record does not assert independent reproduction. ### Llama-3-8B SC (%): 45.48. Result ID: 6995b1ed3badfaffe6b1a8c3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG&SD"}. This record does not assert independent reproduction. ### Gemini-flash SC (%): 45.15. Result ID: 6995b1ed3badfaffe6b1a8bf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG&SD"}. This record does not assert independent reproduction. ### Gemini-flash SC (%): 44.87. Result ID: 6995b1ed3badfaffe6b1a8be. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG+SD"}. This record does not assert independent reproduction. ### GPT-4o SC (%): 43.84. Result ID: 6995b1ed3badfaffe6b1a8bd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG&SD"}. This record does not assert independent reproduction. ### Mistral-small SC (%): 43.34. Result ID: 6995b1ed3badfaffe6b1a8c6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG+SD"}. This record does not assert independent reproduction. ### Mistral-large SC (%): 43.15. Result ID: 6995b1ed3badfaffe6b1a8c8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG+SD"}. This record does not assert independent reproduction. ### Mistral-small SC (%): 41.87. Result ID: 6995b1ed3badfaffe6b1a8c7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG&SD"}. This record does not assert independent reproduction. ### Gemini-pro SC (%): 41.39. Result ID: 6995b1ed3badfaffe6b1a8c0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Approach":"TG+SD"}. This record does not assert independent reproduction. ### GPT-4o SC (%): 39.92. Result ID: 6995b1ed3badfaffe6b1a8bc. [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.