Loading blueprint versions...
Please wait while we gather all the unique runs for this blueprint.
Please wait while we gather all the unique runs for this blueprint.
Please wait while we prepare the detailed comparison.
DTEF: Predict response distributions for Judaism. Source: Global Dialogues GD2 (https://github.com/collect-intel/global-dialogues)
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | Claude Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | Qwen3 30b A3B Instruct 2507 | Qwen3 Next 80b A3B Instruct | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 11th 78.0% | 9th 80.0% | 8th 80.3% | 1st 85.3% | 13th 71.7% | 4th 81.3% | 12th 76.7% | 6th 80.7% | 5th 81.0% | 10th 78.3% | 3rd 81.7% | 2nd 82.7% | 6th 80.7% | |
| 79.4% | 73% | 74% | 74% | 92% | 68% | 86% | 81% | 87% | 76% | 78% | 87% | 77% | 79% | |
| 74.7% | 74% | 84% | 83% | 83% | 74% | 70% | 64% | 71% | 73% | 69% | 71% | 80% | 75% | |
| 85.5% | 87% | 82% | 84% | 81% | 73% | 88% | 85% | 84% | 94% | 88% | 87% | 91% | 88% |