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 | 18th 78.0% | 13th 81.0% | 20th 77.8% | 7th 83.5% | 14th 80.5% | 21st 74.5% | 1st 85.5% | 16th 79.5% | 19th 77.8% | 9th 83.0% | 1st 85.5% | 17th 78.3% | 9th 83.0% | 11th 82.0% | 4th 85.0% | 7th 83.5% | 11th 82.0% | 15th 80.3% | 5th 84.8% | 6th 83.5% | 1st 85.5% | |
| 80.0% | 77% | 77% | 74% | 74% | 73% | 66% | 85% | 80% | 76% | 80% | 89% | 66% | 88% | 92% | 85% | 82% | 81% | 81% | 81% | 80% | 92% | |
| 82.6% | 74% | 86% | 75% | 80% | 69% | 85% | 90% | 72% | 74% | 81% | 89% | 88% | 89% | 74% | 88% | 85% | 88% | 85% | 88% | 87% | 88% | |
| 74.5% | 76% | 79% | 81% | 84% | 81% | 66% | 69% | 70% | 74% | 81% | 80% | 61% | 70% | 72% | 79% | 79% | 67% | 70% | 80% | 74% | 72% | |
| 89.4% | 85% | 82% | 81% | 96% | 99% | 81% | 98% | 96% | 87% | 90% | 84% | 98% | 85% | 90% | 88% | 88% | 92% | 85% | 90% | 93% | 90% |