# Temporal Reasoning Prediction on ICEWS18 (test) Source: [Temporal Reasoning Prediction on ICEWS18 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:58:09.974Z Evaluation of Temporal Reasoning Prediction performance on the test split of the ICEWS18 dataset, measured using classification-style metrics (Positive, Negative, Neutral, Overall). 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 | Temporal Reasoning Prediction | | Dataset (including any stated split) | ICEWS18 (test) | | Metric | Positive Accuracy | | 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 - [Positive Accuracy](): Higher is better; unit: PERCENT. - [Negative Accuracy](): Higher is better; unit: PERCENT. - [Neutral Accuracy](): Higher is better; unit: PERCENT. - [Overall Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Positive Accuracy | Result date | Report paper | | --- | --- | --- | --- | | GETER | 75.78 | Not recorded | 68fa78a61e209131cea799af | | GETER | 75.61 | Not recorded | 68fa78a61e209131cea799af | | GETER | 74.77 | Not recorded | 68fa78a61e209131cea799af | | LoRA | 69.68 | Not recorded | 68fa78a61e209131cea799af | | LoRA | 64.22 | Not recorded | 68fa78a61e209131cea799af | | LoRA | 62.3 | Not recorded | 68fa78a61e209131cea799af | | GPT-4o | 60.33 | Not recorded | 68fa78a61e209131cea799af | | LoRA | 58.07 | Not recorded | 68fa78a61e209131cea799af | | LoRA | 57.47 | Not recorded | 68fa78a61e209131cea799af | | Llama3-8B-Instruct | 55.12 | Not recorded | 68fa78a61e209131cea799af | | GPT-4o | 51.64 | Not recorded | 68fa78a61e209131cea799af | | LoRA | 45.82 | Not recorded | 68fa78a61e209131cea799af | | Qwen2.5-7B-Instruct | 44.22 | Not recorded | 68fa78a61e209131cea799af | | Qwen2.5-7B-Instruct | 30.94 | Not recorded | 68fa78a61e209131cea799af | | Llama3-8B-Instruct | 7.68 | Not recorded | 68fa78a61e209131cea799af | | Mistral-7B-Instruct | 4.14 | Not recorded | 68fa78a61e209131cea799af | | Mistral-7B-Instruct | 1.06 | Not recorded | 68fa78a61e209131cea799af | ### GETER Positive Accuracy: 75.78. Result ID: 699598913badfaffe693d10d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct"}. This record does not assert independent reproduction. ### GETER Positive Accuracy: 75.61. Result ID: 699598913badfaffe693d117. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct"}. This record does not assert independent reproduction. ### GETER Positive Accuracy: 74.77. Result ID: 699598913badfaffe693d112. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### LoRA Positive Accuracy: 69.68. Result ID: 699598913badfaffe693d111. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### LoRA Positive Accuracy: 64.22. Result ID: 699598913badfaffe693d116. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct"}. This record does not assert independent reproduction. ### LoRA Positive Accuracy: 62.3. Result ID: 699598913badfaffe693d10c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct"}. This record does not assert independent reproduction. ### GPT-4o Positive Accuracy: 60.33. Result ID: 699598913badfaffe693d108. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"zero-shot"}. This record does not assert independent reproduction. ### LoRA Positive Accuracy: 58.07. Result ID: 699598913badfaffe693d115. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct","Reasoning Chain":"w/o chains text"}. This record does not assert independent reproduction. ### LoRA Positive Accuracy: 57.47. Result ID: 699598913badfaffe693d10b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct","Reasoning Chain":"w/o chains text"}. This record does not assert independent reproduction. ### Llama3-8B-Instruct Positive Accuracy: 55.12. Result ID: 699598913badfaffe693d10a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"zero-shot"}. This record does not assert independent reproduction. ### GPT-4o Positive Accuracy: 51.64. Result ID: 699598913badfaffe693d107. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"zero-shot w/o chains text"}. This record does not assert independent reproduction. ### LoRA Positive Accuracy: 45.82. Result ID: 699598913badfaffe693d110. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct","Reasoning Chain":"w/o chains text"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Positive Accuracy: 44.22. Result ID: 699598913badfaffe693d10f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"zero-shot"}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Positive Accuracy: 30.94. Result ID: 699598913badfaffe693d10e. [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 Positive Accuracy: 7.68. Result ID: 699598913badfaffe693d109. [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 Positive Accuracy: 4.14. Result ID: 699598913badfaffe693d114. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Type":"zero-shot"}. This record does not assert independent reproduction. ### Mistral-7B-Instruct Positive Accuracy: 1.06. Result ID: 699598913badfaffe693d113. [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.