Question Answering on DeepSearchQA
82.67AccuracyPass
Evaluation results
| Method | Links | |
|---|---|---|
| PassK=82026.04 | 82.67 | |
| PassK=42026.04 | 75.04 | |
| PassK=22026.04 | 65.4 | |
| AggAgentK=82026.04 | 65.33 | |
| BoNK=82026.04 | 64 | |
| AggAgentK=42026.04 | 63.78 | |
| SolAggK=82026.04 | 62 | |
| BoNK=42026.04 | 61.46 | |
| SummAggK=42026.04 | 61.33 | |
| SummAggK=82026.04 | 61.33 | |
| SolAggK=42026.04 | 59.11 | |
| BoNK=22026.04 | 58.02 | |
| SolAggK=22026.04 | 57.78 | |
| AggAgentK=22026.04 | 57.33 | |
| SummAggK=22026.04 | 57.11 | |
| FewToolK=42026.04 | 56.5 | |
| FewToolK=82026.04 | 56 | |
| FewToolK=22026.04 | 55.9 | |
| PassK=12026.04 | 54.42 |