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 3.7 Sonnet | Claude Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT 5 | GPT 5.1 | GPT OSS 120b | GPT OSS 20b | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | Grok 4 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 5th 77.0% | 3rd 81.3% | 4th 77.7% | 16th 71.0% | 1st 83.3% | 2nd 82.7% | 19th 70.3% | 17th 71.0% | 6th 76.0% | 12th 72.0% | 7th 75.7% | 10th 74.0% | 18th 70.7% | 9th 74.3% | 15th 71.3% | 11th 73.7% | 8th 74.7% | 20th 69.7% | 12th 72.0% | 21st 68.0% | 12th 72.0% | |
| 85.9% | 91% | 94% | 94% | 81% | 97% | 92% | 75% | 90% | 87% | 84% | 86% | 79% | 76% | 87% | 85% | 88% | 81% | 91% | 85% | 81% | 79% | |
| 64.5% | 70% | 72% | 65% | 66% | 78% | 84% | 61% | 51% | 65% | 61% | 63% | 62% | 61% | 55% | 72% | 66% | 65% | 53% | 63% | 55% | 66% | |
| 72.3% | 70% | 78% | 74% | 66% | 75% | 72% | 75% | 72% | 76% | 71% | 78% | 81% | 75% | 81% | 57% | 67% | 78% | 65% | 68% | 68% | 71% |