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 GD1 (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 | 2nd 82.0% | 6th 76.3% | 11th 74.0% | 2nd 82.0% | 1st 82.5% | 13th 72.0% | 8th 75.3% | 12th 72.8% | 5th 76.8% | 9th 75.3% | 7th 75.5% | 9th 75.3% | 4th 78.8% | |
| 73.6% | 78% | 66% | 66% | 73% | 74% | 75% | 73% | 71% | 74% | 81% | 79% | 73% | 74% | |
| 80.5% | 84% | 83% | 82% | 84% | 80% | 79% | 76% | 77% | 81% | 81% | 75% | 82% | 82% | |
| 71.6% | 76% | 69% | 74% | 79% | 88% | 65% | 71% | 68% | 67% | 67% | 67% | 69% | 71% | |
| 81.5% | 90% | 87% | 74% | 92% | 88% | 69% | 81% | 75% | 85% | 72% | 81% | 77% | 88% |