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 Christianity. 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 | 3rd 81.0% | 5th 77.7% | 6th 76.3% | 2nd 82.7% | 1st 83.3% | 12th 70.7% | 8th 74.7% | 11th 71.0% | 7th 75.7% | 9th 74.0% | 9th 74.0% | 12th 70.7% | 4th 79.3% | |
| 87.8% | 93% | 94% | 94% | 95% | 92% | 75% | 87% | 84% | 86% | 79% | 87% | 78% | 97% | |
| 66.3% | 72% | 65% | 69% | 78% | 84% | 61% | 65% | 61% | 63% | 62% | 54% | 63% | 65% | |
| 74.6% | 78% | 74% | 66% | 75% | 74% | 76% | 72% | 68% | 78% | 81% | 81% | 71% | 76% |