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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 9th 84.3% | 2nd 88.0% | 13th 83.5% | 15th 82.3% | 12th 83.7% | 6th 84.5% | 18th 81.3% | 21st 78.5% | 14th 82.8% | 5th 84.7% | 10th 84.0% | 18th 81.3% | 3rd 86.8% | 17th 81.8% | 7th 84.5% | 16th 82.0% | 18th 81.3% | 7th 84.5% | 1st 89.3% | 10th 84.0% | 4th 85.3% | |
| 75.3% | 71% | 76% | 66% | 66% | 77% | 68% | 75% | 79% | 80% | 75% | 81% | 83% | 86% | 85% | 68% | 63% | 76% | 76% | 83% | 72% | 76% | |
| 84.9% | 86% | 87% | 87% | 88% | 88% | 85% | 90% | 72% | 78% | 86% | 85% | 80% | 89% | 82% | 85% | 90% | 86% | 89% | 87% | 86% | 76% | |
| 82.0% | 85% | 92% | 85% | 85% | 92% | 92% | 69% | 73% | 80% | 86% | 76% | 71% | 75% | 71% | 90% | 86% | 69% | 79% | 92% | 93% | ||
| 92.5% | 95% | 97% | 96% | 90% | 78% | 93% | 91% | 90% | 93% | 92% | 94% | 91% | 97% | 89% | 95% | 89% | 94% | 94% | 95% | 94% | 96% |