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 | 14th 80.3% | 12th 81.0% | 18th 77.0% | 6th 83.5% | 19th 76.8% | 21st 74.8% | 5th 85.0% | 13th 80.8% | 17th 78.3% | 10th 82.5% | 3rd 85.5% | 20th 76.8% | 7th 83.3% | 15th 79.3% | 1st 86.0% | 11th 81.7% | 9th 82.8% | 15th 79.3% | 7th 83.3% | 2nd 85.5% | 4th 85.3% | |
| 79.4% | 76% | 77% | 71% | 74% | 62% | 66% | 82% | 82% | 75% | 78% | 89% | 63% | 88% | 87% | 91% | 81% | 82% | 85% | 81% | 85% | 92% | |
| 82.4% | 74% | 86% | 75% | 80% | 71% | 83% | 90% | 77% | 74% | 79% | 87% | 88% | 88% | 74% | 87% | 82% | 91% | 86% | 83% | 87% | 88% | |
| 74.6% | 75% | 79% | 81% | 84% | 79% | 68% | 70% | 70% | 74% | 80% | 79% | 60% | 74% | 66% | 81% | 76% | 71% | 67% | 79% | 81% | 73% | |
| 89.0% | 96% | 82% | 81% | 96% | 95% | 82% | 98% | 94% | 90% | 93% | 87% | 96% | 83% | 90% | 85% | 88% | 87% | 79% | 90% | 89% | 88% |