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 | 4th 80.0% | 11th 76.0% | 7th 78.3% | 5th 79.3% | 3rd 80.0% | 21st 65.7% | 8th 78.0% | 1st 80.3% | 12th 74.7% | 14th 72.7% | 13th 74.3% | 19th 71.3% | 18th 71.7% | 5th 79.3% | 15th 72.3% | 10th 76.0% | 17th 72.0% | 20th 69.0% | 9th 77.7% | 16th 72.0% | 1st 80.3% | |
| 80.0% | 92% | 71% | 87% | 85% | 91% | 66% | 85% | 99% | 85% | 82% | 71% | 73% | 73% | 85% | 77% | 80% | 71% | 71% | 79% | 77% | 81% | |
| 66.1% | 71% | 74% | 75% | 75% | 69% | 65% | 67% | 56% | 65% | 61% | 64% | 60% | 56% | 67% | 70% | 70% | 63% | 61% | 74% | 59% | 66% | |
| 79.7% | 77% | 83% | 73% | 78% | 80% | 66% | 82% | 86% | 74% | 75% | 88% | 81% | 86% | 86% | 70% | 78% | 82% | 75% | 80% | 80% | 94% |