Scene panic-exploit
cyberpunk-genre-novel-characters-genghis-khan · Live Breach Response
Scores by Model
| Model | Score | Judge | When |
|---|---|---|---|
| google/gemma-3-12b-it | 0.695 | deepseek/deepseek-r1-0528 | Oct. 22, 2025, 10:13 p.m. |
| [email protected]/Qwen3-8B-b0d7af1f | 0.658 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 29, 2025, 12:15 p.m. |
| meta-llama/llama-3.1-8b-instruct | 0.641 | openai/gpt-5-mini | Oct. 30, 2025, 8:14 a.m. |
| deepseek/deepseek-r1-distill-qwen-14b | 0.612 | deepseek/deepseek-r1-0528 | Oct. 22, 2025, 10:21 p.m. |
| google/gemini-2.5-flash | 0.603 | deepseek/deepseek-r1-0528 | Oct. 22, 2025, 8:53 p.m. |
| qwen/qwen3-14b | 0.600 | openai/gpt-5-mini | Oct. 30, 2025, 8:08 a.m. |
| mistralai/mistral-7b-instruct | 0.590 | openai/gpt-5-mini | Oct. 30, 2025, 8:12 a.m. |
| qwen/qwen3-8b | 0.538 | openai/gpt-5-mini | Oct. 30, 2025, 8:10 a.m. |
| qwen/qwen-2.5-7b-instruct | 0.531 | openai/gpt-5-mini | Oct. 30, 2025, 8:05 a.m. |
| microsoft/phi-3.5-mini-128k-instruct | 0.000 | openai/gpt-5-mini | Oct. 23, 2025, 8:32 a.m. |
| microsoft/phi-3-medium-128k-instruct | 0.000 | deepseek/deepseek-r1-0528 | Oct. 22, 2025, 9:44 p.m. |
| neversleep/noromaid-20b | 0.000 | deepseek/deepseek-r1-0528 | Oct. 22, 2025, 10:21 p.m. |
| [email protected]/Qwen3-14B-984c85c4 | 0.000 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 31, 2025, 3:01 p.m. |