TheBloke/SUS-Chat-34B-GGUF
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| HellaSwag | knowledge | 83.79 | high | | SUS-Chat-34B | 77.35 | 78.68 | 82.42 | 80.06 | 67.62 | 28.8 | 81.22 | 81.54 | 83.79 | 57.47 | 71.895 | | |
| C-Eval | knowledge | 82.42 | high | | SUS-Chat-34B | 77.35 | 78.68 | 82.42 | 80.06 | 67.62 | 28.8 | 81.22 | 81.54 | 83.79 | 57.47 | 71.895 | | |
| WinoGrande | knowledge | 81.22 | high | | SUS-Chat-34B | 77.35 | 78.68 | 82.42 | 80.06 | 67.62 | 28.8 | 81.22 | 81.54 | 83.79 | 57.47 | 71.895 | | |
| GSM8K | math | 80.06 | high | | SUS-Chat-34B | 77.35 | 78.68 | 82.42 | 80.06 | 67.62 | 28.8 | 81.22 | 81.54 | 83.79 | 57.47 | 71.895 | | |
| CMMLU | knowledge | 78.68 | high | | SUS-Chat-34B | 77.35 | 78.68 | 82.42 | 80.06 | 67.62 | 28.8 | 81.22 | 81.54 | 83.79 | 57.47 | 71.895 | | |
| MMLU | knowledge | 77.35 | high | | SUS-Chat-34B | 77.35 | 78.68 | 82.42 | 80.06 | 67.62 | 28.8 | 81.22 | 81.54 | 83.79 | 57.47 | 71.895 | | |
| BBH | reasoning | 67.62 | high | | SUS-Chat-34B | 77.35 | 78.68 | 82.42 | 80.06 | 67.62 | 28.8 | 81.22 | 81.54 | 83.79 | 57.47 | 71.895 | | |
| TruthfulQA | safety | 57.47 | high | | SUS-Chat-34B | 77.35 | 78.68 | 82.42 | 80.06 | 67.62 | 28.8 | 81.22 | 81.54 | 83.79 | 57.47 | 71.895 | | |
| MATH | math | 28.8 | high | | SUS-Chat-34B | 77.35 | 78.68 | 82.42 | 80.06 | 67.62 | 28.8 | 81.22 | 81.54 | 83.79 | 57.47 | 71.895 | |
none scraped.