# Temporal Reasoning on ICEWS05-15 (test) Source: [Temporal Reasoning on ICEWS05-15 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:58:10.175Z Evaluation of Temporal Reasoning performance on the test split of the ICEWS05-15 dataset, measured using classification-style metrics like Positive, Negative, Neutral, and Overall scores. 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 | | Dataset (including any stated split) | ICEWS05-15 (test) | | Metric | Positive Score | | 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 Score](): Higher is better; unit: PERCENT. - [Negative Score](): Higher is better; unit: PERCENT. - [Neutral Score](): Higher is better; unit: PERCENT. - [Overall Score](): Higher is better; unit: PERCENT. ## Recorded results | Method | Positive Score | Result date | Report paper | | --- | --- | --- | --- | | GETER | 78.94 | Not recorded | 68fa78a61e209131cea799af | | GETER | 78.58 | Not recorded | 68fa78a61e209131cea799af | | GETER | 78.23 | Not recorded | 68fa78a61e209131cea799af | | Mistral-7B-Instruct | 72.53 | Not recorded | 68fa78a61e209131cea799af | | Llama3-8B-Instruct | 71.32 | Not recorded | 68fa78a61e209131cea799af | | Mistral-7B-Instruct | 70.81 | Not recorded | 68fa78a61e209131cea799af | | Qwen2.5-7B-Instruct | 66.83 | Not recorded | 68fa78a61e209131cea799af | | Llama3-8B-Instruct | 65.67 | Not recorded | 68fa78a61e209131cea799af | | GPT-4o | 61.63 | Not recorded | 68fa78a61e209131cea799af | | Llama3-8B-Instruct | 57.14 | Not recorded | 68fa78a61e209131cea799af | | GPT-4o | 55.45 | Not recorded | 68fa78a61e209131cea799af | | Qwen2.5-7B-Instruct | 55.33 | Not recorded | 68fa78a61e209131cea799af | | Qwen2.5-7B-Instruct | 40.81 | Not recorded | 68fa78a61e209131cea799af | | Qwen2.5-7B-Instruct | 31.71 | Not recorded | 68fa78a61e209131cea799af | | Mistral-7B-Instruct | 17.73 | Not recorded | 68fa78a61e209131cea799af | | Llama3-8B-Instruct | 11.75 | Not recorded | 68fa78a61e209131cea799af | | Mistral-7B-Instruct | 7.56 | Not recorded | 68fa78a61e209131cea799af | ### GETER Positive Score: 78.94. Result ID: 699598913badfaffe693d0b1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Mistral-7B-Instruct"}. This record does not assert independent reproduction. ### GETER Positive Score: 78.58. Result ID: 699598913badfaffe693d0a7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Llama3-8B-Instruct"}. This record does not assert independent reproduction. ### GETER Positive Score: 78.23. Result ID: 699598913badfaffe693d0ac. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-7B-Instruct"}. This record does not assert independent reproduction. ### Mistral-7B-Instruct Positive Score: 72.53. Result ID: 699598913badfaffe693d0b0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"LoRA","Reasoning Chains":true}. This record does not assert independent reproduction. ### Llama3-8B-Instruct Positive Score: 71.32. Result ID: 699598913badfaffe693d0a6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"LoRA","Reasoning Chains":true}. This record does not assert independent reproduction. ### Mistral-7B-Instruct Positive Score: 70.81. Result ID: 699598913badfaffe693d0af. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"LoRA","Reasoning Chains":false}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Positive Score: 66.83. Result ID: 699598913badfaffe693d0ab. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"LoRA","Reasoning Chains":true}. This record does not assert independent reproduction. ### Llama3-8B-Instruct Positive Score: 65.67. Result ID: 699598913badfaffe693d0a5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"LoRA","Reasoning Chains":false}. This record does not assert independent reproduction. ### GPT-4o Positive Score: 61.63. Result ID: 699598913badfaffe693d0a2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"zero-shot","Reasoning Chains":true}. This record does not assert independent reproduction. ### Llama3-8B-Instruct Positive Score: 57.14. Result ID: 699598913badfaffe693d0a4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"zero-shot","Reasoning Chains":true}. This record does not assert independent reproduction. ### GPT-4o Positive Score: 55.45. Result ID: 699598913badfaffe693d0a1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"zero-shot","Reasoning Chains":false}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Positive Score: 55.33. Result ID: 699598913badfaffe693d0aa. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"LoRA","Reasoning Chains":false}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Positive Score: 40.81. Result ID: 699598913badfaffe693d0a9. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"zero-shot","Reasoning Chains":true}. This record does not assert independent reproduction. ### Qwen2.5-7B-Instruct Positive Score: 31.71. Result ID: 699598913badfaffe693d0a8. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"zero-shot","Reasoning Chains":false}. This record does not assert independent reproduction. ### Mistral-7B-Instruct Positive Score: 17.73. Result ID: 699598913badfaffe693d0ae. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"zero-shot","Reasoning Chains":true}. This record does not assert independent reproduction. ### Llama3-8B-Instruct Positive Score: 11.75. Result ID: 699598913badfaffe693d0a3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"zero-shot","Reasoning Chains":false}. This record does not assert independent reproduction. ### Mistral-7B-Instruct Positive Score: 7.56. Result ID: 699598913badfaffe693d0ad. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Protocol":"zero-shot","Reasoning Chains":false}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.