Scene smear-campaign

courtroom-drama-defense-and-prosecution-teams-characters-bernie-madoff · Attacking a Witness
Clear

Scores by Model

ModelScoreJudgeWhen
deepseek/deepseek-r1-distill-qwen-14b 0.879 deepseek/deepseek-r1-0528 Oct. 22, 2025, 3:16 p.m.
google/gemma-3-12b-it 0.820 deepseek/deepseek-r1-0528 Oct. 22, 2025, 3:05 p.m.
google/gemini-2.5-flash 0.628 deepseek/deepseek-r1-0528 Oct. 22, 2025, 2:14 p.m.
mistralai/mistral-7b-instruct 0.625 openai/gpt-5-mini Oct. 30, 2025, 2:17 a.m.
qwen/qwen-2.5-7b-instruct 0.535 openai/gpt-5-mini Oct. 30, 2025, 2:12 a.m.
qwen/qwen3-14b 0.529 openai/gpt-5-mini Oct. 30, 2025, 2:14 a.m.
[email protected]/Qwen3-8B-b0d7af1f 0.435 meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo Oct. 29, 2025, 11:44 a.m.
meta-llama/llama-3.1-8b-instruct 0.321 openai/gpt-5-mini Oct. 30, 2025, 2:19 a.m.
qwen/qwen3-8b 0.067 openai/gpt-5-mini Oct. 30, 2025, 2:15 a.m.
microsoft/phi-3.5-mini-128k-instruct 0.000 deepseek/deepseek-r1-0528 Oct. 22, 2025, 3:11 p.m.
microsoft/phi-3-medium-128k-instruct 0.000 deepseek/deepseek-r1-0528 Oct. 22, 2025, 2:48 p.m.
neversleep/noromaid-20b 0.000 openai/gpt-5-mini Oct. 23, 2025, 8:27 a.m.
[email protected]/Qwen3-14B-984c85c4 0.000 meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo Oct. 31, 2025, 2:40 p.m.