Qwen/Qwen2-1.5B
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| WinoGrande | knowledge | 74.4 | Winogrande | medium | | Winogrande | **74.4** | 66.8 | - | 60.3 | 56.8 | 66.2 | |
| HellaSwag | knowledge | 73.1 | HellaSwag | medium | | HellaSwag | **73.1** | 71.4 | 68.3 | 61.4 | 49.3 | 66.6 | |
| GSM8K | math | 57.2 | GSM8K | medium | | GSM8K | 57.2 | 17.7 | 53.8 | 38.4 | 36.5 | **58.5** | |
| MBPP | coding | 55.0 | MBPP | medium | | MBPP | **55.0** | 29.2 | 47.3 | 18.0 | 22.0 | 37.4 | |
| MMLU | knowledge | 52.7 | MMLU | medium | | MMLU | 52.7 | 42.3 | 53.5 | 46.8 | 45.4 | **56.5** | |
| HumanEval | coding | 47.6 | HumanEval | medium | | HumanEval | 47.6 | 22.0 | **50.0** | 20.1 | 22.0 | 31.1 | |
| TruthfulQA | safety | 44.5 | TruthfulQA | medium | | TruthfulQA | 44.5 | 33.1 | - | 39.4 | 39.7 | **45.9** | |
| BBH | reasoning | 43.4 | BBH | medium | | BBH | **43.4** | 35.2 | 36.9 | 24.2 | 28.4 | 37.2 | |
| CMMLU | knowledge | 24.2 | CMMLU | medium | | CMMLU | 24.2 | - | 51.1 | 57.8 | 55.1 | **70.3** | |
| C-Eval | knowledge | 23.4 | C-Eval | medium | | C-Eval | 23.4 | 28.0 | 51.1 | 59.7 | 58.2 | **70.6** | |
| MMLU-Pro | knowledge | 15.9 | MMLU-Pro | medium | | MMLU-Pro | - | 15.9 | - | - | 14.7 | 21.8 | |
| MATH | math | 3.5 | MATH | medium | | MATH | 3.5 | 11.8 | 10.2 | 10.1 | 10.7 | **21.7** | |
none scraped.