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 | 4th 78.3% | 3rd 80.8% | 5th 78.0% | 12th 74.3% | 1st 82.8% | 2nd 82.3% | 16th 71.3% | 18th 69.8% | 9th 75.8% | 15th 72.0% | 7th 76.8% | 11th 74.5% | 14th 73.5% | 8th 76.0% | 17th 70.8% | 13th 73.8% | 10th 74.8% | 19th 69.0% | 6th 77.0% | 21st 60.2% | 20th 66.8% | |
| 71.0% | 69% | 76% | 73% | 66% | 73% | 74% | 75% | 76% | 75% | 68% | 75% | 79% | 75% | 79% | 55% | 67% | 75% | 66% | 73% | 57% | 64% | |
| 76.5% | 73% | 84% | 83% | 83% | 84% | 80% | 79% | 68% | 76% | 76% | 81% | 80% | 80% | 71% | 71% | 78% | 76% | 78% | 85% | 60% | 60% | |
| 69.7% | 80% | 76% | 69% | 74% | 83% | 89% | 65% | 54% | 71% | 68% | 64% | 67% | 67% | 68% | 81% | 78% | 68% | 47% | 67% | 59% | 68% | |
| 79.7% | 91% | 87% | 87% | 74% | 91% | 86% | 66% | 81% | 81% | 76% | 87% | 72% | 72% | 86% | 76% | 72% | 80% | 85% | 83% | 65% | 75% |