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 I do not identify with any religious group or faith. 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 76.8% | 4th 79.8% | 14th 75.5% | 6th 78.3% | 8th 77.0% | 18th 70.5% | 1st 82.0% | 17th 72.8% | 16th 74.3% | 13th 75.5% | 11th 76.5% | 15th 74.5% | 7th 77.8% | 9th 76.8% | 3rd 80.3% | 2nd 81.5% | 12th 75.8% | 21st 67.8% | 5th 79.3% | 19th 70.2% | 20th 68.3% | |
| 76.7% | 74% | 84% | 75% | 74% | 78% | 63% | 85% | 82% | 66% | 79% | 79% | 79% | 87% | 83% | 71% | 80% | 79% | 65% | 72% | 79% | 77% | |
| 68.9% | 73% | 76% | 61% | 65% | 59% | 70% | 84% | 63% | 71% | 66% | 71% | 57% | 78% | 71% | 73% | 80% | 79% | 77% | 80% | 61% | 31% | |
| 70.2% | 75% | 78% | 79% | 84% | 86% | 63% | 74% | 53% | 70% | 70% | 65% | 74% | 56% | 61% | 87% | 78% | 57% | 44% | 75% | 67% | 78% | |
| 87.2% | 85% | 81% | 87% | 90% | 85% | 86% | 85% | 93% | 90% | 87% | 91% | 88% | 90% | 92% | 90% | 88% | 88% | 85% | 90% | 74% | 87% |