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 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 | 7th 84.7% | 1st 88.5% | 9th 83.8% | 13th 82.5% | 19th 79.5% | 9th 83.8% | 16th 81.5% | 20th 79.0% | 6th 84.8% | 8th 84.3% | 5th 85.5% | 14th 81.8% | 3rd 86.5% | 18th 81.3% | 14th 81.8% | 9th 83.8% | 9th 83.8% | 16th 81.5% | 2nd 87.5% | 21st 78.8% | 4th 86.3% | |
| 75.4% | 72% | 76% | 67% | 66% | 73% | 68% | 75% | 79% | 80% | 73% | 81% | 84% | 85% | 83% | 67% | 75% | 74% | 74% | 80% | 76% | 76% | |
| 85.1% | 87% | 90% | 87% | 89% | 78% | 85% | 90% | 72% | 78% | 83% | 90% | 80% | 89% | 82% | 86% | 89% | 85% | 85% | 85% | 83% | 94% | |
| 81.4% | 85% | 92% | 85% | 85% | 92% | 89% | 69% | 76% | 88% | 86% | 76% | 71% | 75% | 71% | 78% | 87% | 83% | 81% | 90% | 62% | 89% | |
| 91.5% | 95% | 96% | 96% | 90% | 75% | 93% | 92% | 89% | 93% | 95% | 95% | 92% | 97% | 89% | 96% | 84% | 93% | 86% | 95% | 94% | 86% |