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 79.5% | 10th 81.0% | 20th 76.8% | 8th 83.5% | 19th 76.8% | 21st 73.8% | 1st 86.0% | 13th 80.0% | 17th 77.5% | 9th 82.3% | 2nd 85.0% | 12th 80.3% | 14th 79.5% | 10th 81.0% | 7th 83.8% | 5th 84.3% | 6th 84.2% | 16th 78.8% | 3rd 84.8% | 18th 77.0% | 4th 84.5% | |
| 79.3% | 74% | 77% | 71% | 74% | 63% | 66% | 85% | 80% | 72% | 80% | 88% | 81% | 88% | 93% | 77% | 88% | 82% | 81% | 81% | 77% | 87% | |
| 81.8% | 80% | 86% | 74% | 80% | 68% | 83% | 91% | 73% | 74% | 76% | 92% | 88% | 78% | 74% | 88% | 84% | 83% | 88% | 88% | 81% | 88% | |
| 74.5% | 73% | 79% | 81% | 84% | 80% | 64% | 70% | 70% | 74% | 80% | 79% | 56% | 69% | 67% | 80% | 82% | 78% | 71% | 79% | 75% | 73% | |
| 88.3% | 91% | 82% | 81% | 96% | 96% | 82% | 98% | 97% | 90% | 93% | 81% | 96% | 83% | 90% | 90% | 83% | 94% | 75% | 91% | 75% | 90% |