| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| History factoid QA (test) | NABoE-full | Accuracy94.9 | 25 | 4mo ago | |
| Quiz Bowl Literature category | NABoE-full | Accuracy98.5 | 16 | 4mo ago | |
| Trivia Estonian | Llama-EstLLM-8B-Instruct-CV | Accuracy42.9 | 10 | 4mo ago | |
| Literature factoid QA (test) | NTEE | Accuracy95.1 | 9 | 4mo ago | |
| Factoid benchmarks (LAMA, EntityQA, WebQA) (test) | REMIX | LAMA Accuracy90.5 | 6 | 26d ago | |
| BioASQ Task B | Strict Score55.05 | 6 | 3mo ago | ||
| TriviaQA | Score42.85 | 6 | 3mo ago | ||
| BioASQ-factoid Challenge 7h (live runs) | ELECTRAMed | Batch 1 Score1 | 5 | 4mo ago | |
| BioASQ Average across batches 14b | ku_dmis | Strict Accuracy38.78 | 1 | 17d ago | |
| BioASQ-14b Batch 4 | ku_dmis | Strict Score45.45 | 1 | 17d ago | |
| BioASQ Batch 3 14b | ku_dmis | Strict Score41.18 | 1 | 17d ago | |
| BioASQ-14b Batch 2 | ku_dmis | Strict Score25 | 1 | 17d ago | |
| BioASQ Batch 1 14b | ku_dmis | Strict Accuracy43.48 | 1 | 17d ago |