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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 19th 78.0% | 13th 81.0% | 19th 78.0% | 6th 83.5% | 17th 79.0% | 21st 74.5% | 2nd 85.8% | 15th 80.0% | 18th 78.5% | 9th 82.5% | 3rd 85.0% | 10th 82.3% | 8th 82.8% | 11th 81.5% | 14th 80.0% | 1st 86.0% | 12th 81.3% | 4th 84.3% | 5th 83.8% | 16th 79.3% | 6th 83.5% | |
| 80.4% | 75% | 77% | 75% | 74% | 67% | 66% | 82% | 82% | 78% | 80% | 89% | 80% | 87% | 87% | 83% | 84% | 84% | 81% | 80% | 81% | 96% | |
| 83.0% | 77% | 86% | 75% | 80% | 78% | 85% | 92% | 79% | 74% | 79% | 87% | 90% | 89% | 74% | 89% | 84% | 79% | 88% | 84% | 85% | 88% | |
| 74.6% | 72% | 79% | 81% | 84% | 77% | 65% | 72% | 70% | 75% | 80% | 79% | 61% | 68% | 72% | 63% | 81% | 75% | 81% | 80% | 76% | 75% | |
| 87.9% | 88% | 82% | 81% | 96% | 94% | 82% | 97% | 89% | 87% | 91% | 85% | 98% | 87% | 93% | 85% | 95% | 87% | 87% | 91% | 75% | 75% |