List your company

Narrative Detective Stories Human Subjective Evaluation (test)

3.96Surprise ScoreLlama 3.1-8B
2.74323.05913.3753.6909Jul 18, 2025

Evaluation results

MethodLinks
Llama 3.1-8Bnumber of stories=242025.073.962.752.672.5
Gemini 2.5 flash TB 0number of stories=302025.073.82.673.273
Poirotnumber of stories=372025.073.74.034.514.11
GPT-4o mininumber of stories=232025.073.612.572.742.35
Gemini 2.5-pronumber of stories=292025.073.53.113.723.41
Gemini 2.5 flash TB -1number of stories=302025.073.472.62.92.53
Avg. generatednumber of stories=2902025.073.442.772.992.65
GPT-4onumber of stories=262025.073.423.233.733.39
Llama 3.1-70Bnumber of stories=262025.073.392.582.692.58
Llama 3.3-70Bnumber of stories=552025.073.382.42.472.29
Avg. realnumber of stories=702025.073.323.914.394.21
Gemini 1.5-pronumber of stories=192025.073.113.163.422.42
Sherlocknumber of stories=332025.073.093.854.214.3
Llama 3.2-3Bnumber of stories=282025.072.793.182.682.39