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 | 13th 77.0% | 9th 78.3% | 7th 80.7% | 4th 82.7% | 2nd 83.3% | 19th 74.0% | 6th 82.3% | 16th 76.3% | 18th 74.3% | 8th 80.3% | 9th 78.3% | 17th 75.7% | 9th 78.3% | 13th 77.0% | 3rd 83.0% | 4th 82.7% | 15th 76.7% | 21st 70.0% | 12th 77.7% | 20th 71.0% | 1st 84.3% | |
| 84.6% | 74% | 71% | 85% | 85% | 91% | 84% | 86% | 95% | 86% | 91% | 86% | 83% | 86% | 85% | 91% | 82% | 83% | 77% | 84% | 79% | 93% | |
| 70.6% | 81% | 79% | 79% | 85% | 77% | 72% | 73% | 51% | 69% | 70% | 64% | 60% | 62% | 61% | 82% | 82% | 67% | 52% | 75% | 65% | 76% | |
| 79.7% | 76% | 85% | 78% | 78% | 82% | 66% | 88% | 83% | 68% | 80% | 85% | 84% | 87% | 85% | 76% | 84% | 80% | 81% | 74% | 69% | 84% |