TheBloke/openchat-3.5-0106-GGUF
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| GSM8K | math | 77.3 | BBH CoT | high | | OpenChat-3.5 | **7B** | 61.6 | 7.81 | 55.5 | 47.6 | 47.4 | 59.1 | 64.3 | 77.3 | 63.5 | |
| GSM8K | math | 77.3 | high | | OpenChat-3.5 | Apache-2.0 | **7B** | 56.4 | 64.3 | 55.5 | 28.6 | 77.3 | | |
| MMLU | knowledge | 64.3 | BBH CoT | high | | OpenChat-3.5 | **7B** | 61.6 | 7.81 | 55.5 | 47.6 | 47.4 | 59.1 | 64.3 | 77.3 | 63.5 | |
| MMLU | knowledge | 64.3 | high | | OpenChat-3.5 | Apache-2.0 | **7B** | 56.4 | 64.3 | 55.5 | 28.6 | 77.3 | | |
| TruthfulQA | safety | 59.1 | BBH CoT | high | | OpenChat-3.5 | **7B** | 61.6 | 7.81 | 55.5 | 47.6 | 47.4 | 59.1 | 64.3 | 77.3 | 63.5 | |
| HumanEval | coding | 55.5 | BBH CoT | high | | OpenChat-3.5 | **7B** | 61.6 | 7.81 | 55.5 | 47.6 | 47.4 | 59.1 | 64.3 | 77.3 | 63.5 | |
| HumanEval | coding | 55.5 | high | | OpenChat-3.5 | Apache-2.0 | **7B** | 56.4 | 64.3 | 55.5 | 28.6 | 77.3 | | |
| BBH | reasoning | 47.6 | BBH CoT | high | | OpenChat-3.5 | **7B** | 61.6 | 7.81 | 55.5 | 47.6 | 47.4 | 59.1 | 64.3 | 77.3 | 63.5 | |
| AGIEval | reasoning | 47.4 | BBH CoT | high | | OpenChat-3.5 | **7B** | 61.6 | 7.81 | 55.5 | 47.6 | 47.4 | 59.1 | 64.3 | 77.3 | 63.5 | |
| MATH | math | 28.6 | high | | OpenChat-3.5 | Apache-2.0 | **7B** | 56.4 | 64.3 | 55.5 | 28.6 | 77.3 | | |
| MT-Bench | chat | 7.81 | BBH CoT | high | | OpenChat-3.5 | **7B** | 61.6 | 7.81 | 55.5 | 47.6 | 47.4 | 59.1 | 64.3 | 77.3 | 63.5 | |
none scraped.