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 | 4th 79.2% | 3rd 79.5% | 6th 76.3% | 13th 74.0% | 2nd 81.0% | 1st 82.5% | 16th 72.8% | 11th 74.3% | 11th 74.3% | 15th 73.0% | 7th 75.8% | 10th 74.5% | 17th 72.5% | 8th 75.5% | 20th 69.8% | 18th 72.2% | 9th 75.0% | 5th 76.8% | 13th 74.0% | 21st 61.3% | 19th 70.5% | |
| 71.0% | 69% | 78% | 66% | 66% | 78% | 74% | 75% | 75% | 71% | 71% | 74% | 79% | 74% | 79% | 55% | 59% | 74% | 71% | 70% | 64% | 70% | |
| 77.7% | 82% | 84% | 83% | 82% | 79% | 80% | 79% | 68% | 76% | 80% | 81% | 80% | 79% | 79% | 73% | 78% | 79% | 75% | 82% | 60% | 73% | |
| 69.8% | 76% | 69% | 69% | 74% | 75% | 88% | 67% | 71% | 69% | 65% | 61% | 67% | 65% | 67% | 73% | 72% | 68% | 76% | 67% | 59% | 67% | |
| 79.5% | 90% | 87% | 87% | 74% | 92% | 88% | 70% | 83% | 81% | 76% | 87% | 72% | 72% | 77% | 78% | 80% | 79% | 85% | 77% | 62% | 72% |