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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 6th 78.7% | 14th 74.0% | 8th 78.3% | 3rd 79.3% | 1st 80.3% | 21st 65.7% | 9th 77.7% | 1st 80.3% | 11th 75.0% | 13th 74.3% | 16th 73.7% | 10th 76.7% | 19th 72.7% | 4th 79.0% | 17th 73.3% | 4th 79.0% | 12th 74.7% | 20th 71.0% | 7th 78.3% | 14th 74.0% | 17th 73.3% | |
| 80.9% | 87% | 71% | 87% | 85% | 96% | 66% | 86% | 99% | 86% | 84% | 71% | 83% | 82% | 85% | 74% | 79% | 74% | 64% | 80% | 85% | 74% | |
| 65.7% | 72% | 71% | 74% | 75% | 65% | 60% | 66% | 56% | 65% | 61% | 63% | 60% | 59% | 62% | 71% | 73% | 65% | 69% | 72% | 57% | 63% | |
| 80.5% | 77% | 80% | 74% | 78% | 80% | 71% | 81% | 86% | 74% | 78% | 87% | 87% | 77% | 90% | 75% | 85% | 85% | 80% | 83% | 80% | 83% |