Scene compilation-rant
loony-toons-leon-schlesinger · Long-form rant over 30-minute compilation
Scores by Model
| Model | Score | Judge | When |
|---|---|---|---|
| deepseek/deepseek-r1-distill-qwen-14b | 0.437 | openai/gpt-5-mini | Sept. 24, 2025, 5:54 p.m. |
| [email protected]/Qwen3-8B-da5790fa | 0.408 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 10, 2025, 11:25 a.m. |
| qwen/qwen-2.5-7b-instruct | 0.381 | openai/gpt-5-mini | Sept. 24, 2025, 5:41 p.m. |
| mistralai/mistral-7b-instruct | 0.377 | openai/gpt-5-mini | Sept. 24, 2025, 5:46 p.m. |
| [email protected]/Qwen2.5-7B-Instruct-521d3af9 | 0.335 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 10, 2025, 8:47 a.m. |
| neversleep/noromaid-20b | 0.316 | openai/gpt-5-mini | Sept. 24, 2025, 5:56 p.m. |
| google/gemini-2.5-flash | 0.308 | openai/gpt-5-mini | Sept. 24, 2025, 5:39 p.m. |
| google/gemma-3-12b-it | 0.294 | openai/gpt-5-mini | Sept. 24, 2025, 5:51 p.m. |
| meta-llama/llama-3.1-8b-instruct | 0.266 | openai/gpt-5-mini | Sept. 24, 2025, 5:50 p.m. |
| [email protected]/Qwen3-8B-b0d7af1f | 0.254 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 29, 2025, 9:10 a.m. |
| qwen/qwen3-14b | 0.250 | openai/gpt-5-mini | Sept. 24, 2025, 5:43 p.m. |
| [email protected]/Qwen3-14B-e66d90ff | 0.055 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 10, 2025, 1:30 p.m. |
| microsoft/phi-3-medium-128k-instruct | 0.003 | openai/gpt-5-mini | Sept. 24, 2025, 5:48 p.m. |
| microsoft/phi-3.5-mini-128k-instruct | 0.000 | openai/gpt-5-mini | Sept. 24, 2025, 5:53 p.m. |
| [email protected]/Qwen3-14B-984c85c4 | 0.000 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 31, 2025, 8:06 a.m. |
| qwen/qwen3-8b | 0.000 | openai/gpt-5-mini | Sept. 24, 2025, 5:45 p.m. |