# Temporal Knowledge Graph Question Answering on Timeline-ICEWS (test) Source: [Temporal Knowledge Graph Question Answering on Timeline-ICEWS (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:54:25.507Z Evaluation of model performance on the test split of the Timeline-ICEWS dataset for Temporal Knowledge Graph Question Answering, broken down by question complexity (Overall, Simple, Medium, Complex). 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 Knowledge Graph Question Answering | | Dataset (including any stated split) | Timeline-ICEWS (test) | | Metric | Overall Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 - [Overall Accuracy](): Higher is better; unit: PERCENT. - [Simple Accuracy](): Higher is better; unit: PERCENT. - [Medium Accuracy](): Higher is better; unit: PERCENT. - [Complex Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Overall Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Temp-R1 | 64.2 | Not recorded | 697846cea2b28e761d87c748 | | PoK | 60.2 | Not recorded | 697846cea2b28e761d87c748 | | TKG-Thinker (Qwen2.5-7B-Instruct) | 50.8 | Not recorded | 698575d3c97a0b3e3b5d5e4f | | TKG-Thinker (Llama3-8B-Instruct) | 46.2 | Not recorded | 698575d3c97a0b3e3b5d5e4f | | RAG baseline | 26.5 | Not recorded | 698575d3c97a0b3e3b5d5e4f | | RAG Baseline | 26.5 | Not recorded | 697846cea2b28e761d87c748 | | GPT-4o | 11.3 | Not recorded | 698575d3c97a0b3e3b5d5e4f | | GPT-4o | 11.3 | Not recorded | 697846cea2b28e761d87c748 | | LLaMA2-7B | 11.1 | Not recorded | 698575d3c97a0b3e3b5d5e4f | | LLaMA2-7B | 11.1 | Not recorded | 697846cea2b28e761d87c748 | ### Temp-R1 Overall Accuracy: 64.2. Result ID: 69966c145698665ec4b2da27. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Llama3.1-8B-Instruct"}. This record does not assert independent reproduction. ### PoK Overall Accuracy: 60.2. Result ID: 69966c145698665ec4b2da26. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### TKG-Thinker (Qwen2.5-7B-Instruct) Overall Accuracy: 50.8. Result ID: 699601135698665ec43743b3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Qwen2.5-7B-Instruct","framework":"TKG-Thinker"}. This record does not assert independent reproduction. ### TKG-Thinker (Llama3-8B-Instruct) Overall Accuracy: 46.2. Result ID: 699601135698665ec43743b4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"base\_model":"Llama3-8B-Instruct","framework":"TKG-Thinker"}. This record does not assert independent reproduction. ### RAG baseline Overall Accuracy: 26.5. Result ID: 699601135698665ec43743b0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### RAG Baseline Overall Accuracy: 26.5. Result ID: 69966c145698665ec4b2da23. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-4o Overall Accuracy: 11.3. Result ID: 699601135698665ec43743b2. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT-4o Overall Accuracy: 11.3. Result ID: 69966c145698665ec4b2da25. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLaMA2-7B Overall Accuracy: 11.1. Result ID: 699601135698665ec43743b1. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### LLaMA2-7B Overall Accuracy: 11.1. Result ID: 69966c145698665ec4b2da24. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.