Mungert/SmolLM2-1.7B-Instruct-GGUF
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| PIQA | knowledge | 77.6 | PIQA | medium | | PIQA | **77.6** | 74.8 | 76.1 | 76.0 | |
| HellaSwag | knowledge | 68.7 | HellaSwag | medium | | HellaSwag | **68.7** | 61.2 | 66.4 | 62.9 | |
| WinoGrande | knowledge | 59.4 | Winogrande | medium | | Winogrande | **59.4** | 57.8 | 59.3 | 54.7 | |
| IFEval | instruction-following | 56.7 | IFEval (Average prompt/inst) | medium | | IFEval (Average prompt/inst) | **56.7** | 53.5 | 47.4 | 23.1 | |
| CommonsenseQA | knowledge | 43.6 | CommonsenseQA | medium | | CommonsenseQA | **43.6** | 41.2 | 34.1 | 38.0 | |
| OpenBookQA | knowledge | 42.2 | OpenBookQA | medium | | OpenBookQA | 42.2 | 38.4 | 40.0 | **42.4** | |
| TriviaQA | knowledge | 36.7 | TriviaQA | medium | | TriviaQA | **36.7** | 28.1 | 20.9 | 22.5 | |
| BBH | reasoning | 32.2 | BBH (3-shot) | medium | | BBH (3-shot) | 32.2 | 27.6 | **35.3** | 25.7 | |
| GSM8K | math | 31.0 | GSM8K (5-shot) | medium | | GSM8K (5-shot) | 31.0 | 7.2 | **61.3** | 5.5 | |
| MMLU-Pro | knowledge | 19.4 | MMLU-Pro (MCF) | medium | | MMLU-Pro (MCF) | **19.4** | 11.7 | 13.7 | 10.8 | |
| MT-Bench | chat | 6.13 | MT-Bench | medium | | MT-Bench | 6.13 | 5.48 | **6.52** | 4.33 | |
none scraped.