Scene twitter-roast
standup-comedians-andrew-dice-clay · Mock Apology Tweet
Scores by Model
| Model | Score | Judge | When |
|---|---|---|---|
| [email protected]/Qwen2.5-7B-Instruct-521d3af9 | 0.848 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 10, 2025, 9:01 a.m. |
| google/gemini-2.5-flash | 0.845 | openai/gpt-5-mini | Sept. 25, 2025, 3:02 a.m. |
| qwen/qwen3-8b | 0.777 | openai/gpt-5-mini | Sept. 25, 2025, 3:06 a.m. |
| [email protected]/Qwen3-8B-b0d7af1f | 0.768 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 29, 2025, 10:02 a.m. |
| [email protected]/Qwen3-8B-da5790fa | 0.748 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 10, 2025, 11:40 a.m. |
| meta-llama/llama-3.1-8b-instruct | 0.727 | openai/gpt-5-mini | Sept. 25, 2025, 3:13 a.m. |
| [email protected]/Qwen3-14B-e66d90ff | 0.712 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 10, 2025, 1:49 p.m. |
| qwen/qwen3-14b | 0.679 | openai/gpt-5-mini | Sept. 25, 2025, 3:04 a.m. |
| qwen/qwen-2.5-7b-instruct | 0.673 | openai/gpt-5-mini | Sept. 25, 2025, 3:03 a.m. |
| google/gemma-3-12b-it | 0.672 | openai/gpt-5-mini | Sept. 25, 2025, 3:15 a.m. |
| deepseek/deepseek-r1-distill-qwen-14b | 0.575 | openai/gpt-5-mini | Sept. 25, 2025, 3:18 a.m. |
| mistralai/mistral-7b-instruct | 0.545 | openai/gpt-5-mini | Sept. 25, 2025, 3:07 a.m. |
| neversleep/noromaid-20b | 0.530 | openai/gpt-5-mini | Sept. 25, 2025, 3:19 a.m. |
| microsoft/phi-3.5-mini-128k-instruct | 0.440 | openai/gpt-5-mini | Sept. 25, 2025, 3:16 a.m. |
| microsoft/phi-3-medium-128k-instruct | 0.000 | openai/gpt-5-mini | Sept. 25, 2025, 3:12 a.m. |
| [email protected]/Qwen3-14B-984c85c4 | 0.000 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 31, 2025, 12:52 p.m. |