Scene award-interview
entertainment-media-film-director-characters-roman-polanski · Press Allegations
Scores by Model
| Model | Score | Judge | When |
|---|---|---|---|
| deepseek/deepseek-r1-distill-qwen-14b | 0.943 | deepseek/deepseek-r1-0528 | Oct. 23, 2025, 5:02 a.m. |
| google/gemini-2.5-flash | 0.912 | deepseek/deepseek-r1-0528 | Oct. 23, 2025, 3:09 a.m. |
| neversleep/noromaid-20b | 0.858 | deepseek/deepseek-r1-0528 | Oct. 23, 2025, 5:05 a.m. |
| google/gemma-3-12b-it | 0.849 | deepseek/deepseek-r1-0528 | Oct. 23, 2025, 4:51 a.m. |
| mistralai/mistral-7b-instruct | 0.788 | openai/gpt-5-mini | Oct. 30, 2025, 1:34 p.m. |
| qwen/qwen3-8b | 0.700 | openai/gpt-5-mini | Oct. 30, 2025, 1:32 p.m. |
| qwen/qwen3-14b | 0.682 | openai/gpt-5-mini | Oct. 30, 2025, 1:30 p.m. |
| qwen/qwen-2.5-7b-instruct | 0.647 | openai/gpt-5-mini | Oct. 30, 2025, 1:27 p.m. |
| microsoft/phi-3.5-mini-128k-instruct | 0.118 | deepseek/deepseek-r1-0528 | Oct. 23, 2025, 4:58 a.m. |
| meta-llama/llama-3.1-8b-instruct | 0.000 | openai/gpt-5-mini | Oct. 30, 2025, 1:36 p.m. |
| microsoft/phi-3-medium-128k-instruct | 0.000 | deepseek/deepseek-r1-0528 | Oct. 23, 2025, 4:22 a.m. |
| [email protected]/Qwen3-14B-984c85c4 | 0.000 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 31, 2025, 3:21 p.m. |
| [email protected]/Qwen3-8B-b0d7af1f | 0.000 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 31, 2025, 2:44 a.m. |