Scene scene_2
marc-marquez · Recovery
Scores by Model
| Model | Score | Judge | When |
|---|---|---|---|
| qwen/qwen3-8b | 0.819 | openai/gpt-5-mini | Sept. 24, 2025, 6:05 p.m. |
| qwen/qwen3-14b | 0.817 | openai/gpt-5-mini | Sept. 24, 2025, 6:01 p.m. |
| qwen/qwen-2.5-7b-instruct | 0.748 | openai/gpt-5-mini | Sept. 24, 2025, 5:58 p.m. |
| google/gemma-3-12b-it | 0.744 | openai/gpt-5-mini | Sept. 24, 2025, 6:38 p.m. |
| [email protected]/Qwen3-8B-b0d7af1f | 0.740 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 29, 2025, 9:11 a.m. |
| microsoft/phi-3.5-mini-128k-instruct | 0.730 | openai/gpt-5-mini | Sept. 24, 2025, 6:40 p.m. |
| deepseek/deepseek-r1-distill-qwen-14b | 0.702 | openai/gpt-5-mini | Sept. 24, 2025, 6:41 p.m. |
| [email protected]/Qwen3-8B-da5790fa | 0.650 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 10, 2025, 11:25 a.m. |
| meta-llama/llama-3.1-8b-instruct | 0.602 | openai/gpt-5-mini | Sept. 24, 2025, 6:35 p.m. |
| [email protected]/Qwen3-14B-e66d90ff | 0.548 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 10, 2025, 1:31 p.m. |
| google/gemini-2.5-flash | 0.489 | openai/gpt-5-mini | Sept. 24, 2025, 5:57 p.m. |
| mistralai/mistral-7b-instruct | 0.440 | openai/gpt-5-mini | Sept. 24, 2025, 6:09 p.m. |
| microsoft/phi-3-medium-128k-instruct | 0.028 | openai/gpt-5-mini | Sept. 24, 2025, 6:19 p.m. |
| neversleep/noromaid-20b | 0.000 | openai/gpt-5-mini | Sept. 24, 2025, 6:43 p.m. |
| [email protected]/Qwen2.5-7B-Instruct-521d3af9 | 0.000 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 10, 2025, 8:48 a.m. |
| [email protected]/Qwen3-14B-984c85c4 | 0.000 | meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Oct. 31, 2025, 8:08 a.m. |