> Starling-7B-alpha scores 8.09 in MT Bench with GPT-4 as a judge, outperforming...

		tosh on Nov 29, 2023 \| parent \| context \| favorite \| on: Starling-7B: Increasing LLM Helpfulness and Harmle... > Starling-7B-alpha scores 8.09 in MT Bench with GPT-4 as a judge, outperforming every model to date on MT-Bench except for OpenAI’s GPT-4 and GPT-4 Turbo.