Entity counting
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Entity counting | Entity counting Qwen3-8B prompts N=200x3 seeds (test) | Greedy Generation Accuracy97 | 7 | |
| Entity counting | Entity counting 200 prompts Qwen3-8B (test) | Accuracy98.7 | 5 |
Showing 2 of 2 rows