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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 80.7% | 5th 80.3% | 13th 72.0% | 13th 72.0% | 1st 82.7% | 1st 82.7% | 17th 70.7% | 13th 72.0% | 6th 77.3% | 13th 72.0% | 8th 75.7% | 10th 74.0% | 17th 70.7% | 9th 74.7% | 20th 42.3% | 10th 74.0% | 7th 76.3% | 4th 80.3% | 12th 74.0% | 19th 68.7% | |
| 81.1% | 91% | 94% | 77% | 81% | 94% | 92% | 75% | 90% | 87% | 84% | 86% | 79% | 76% | 87% | 0% | 87% | 86% | 93% | 85% | 79% | |
| 65.4% | 76% | 65% | 65% | 69% | 75% | 84% | 61% | 51% | 66% | 61% | 63% | 62% | 61% | 55% | 72% | 68% | 65% | 67% | 63% | 59% | |
| 74.4% | 75% | 82% | 74% | 66% | 79% | 72% | 76% | 75% | 79% | 71% | 78% | 81% | 75% | 82% | 55% | 67% | 78% | 81% | 74% | 68% |