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 GD2 (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 | 6th 79.0% | 15th 73.0% | 8th 78.3% | 5th 79.3% | 6th 79.0% | 20th 67.3% | 10th 75.5% | 4th 79.7% | 11th 74.3% | 11th 74.3% | 16th 73.0% | 17th 71.7% | 13th 74.0% | 1st 82.0% | 3rd 80.3% | 8th 78.3% | 14th 73.3% | 19th 69.0% | 2nd 81.3% | 18th 70.5% | 21st 57.7% | |
| 78.8% | 86% | 71% | 87% | 85% | 91% | 66% | 85% | 98% | 85% | 87% | 71% | 77% | 85% | 85% | 86% | 75% | 69% | 68% | 79% | 77% | 41% | |
| 66.5% | 73% | 68% | 75% | 75% | 65% | 65% | 66% | 55% | 64% | 63% | 63% | 57% | 60% | 67% | 72% | 76% | 67% | 59% | 79% | 64% | 64% | |
| 79.8% | 78% | 80% | 73% | 78% | 81% | 71% | 86% | 74% | 73% | 85% | 81% | 77% | 94% | 83% | 84% | 84% | 80% | 86% | 68% |