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 Other religious group. 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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 7th 70.0% | 2nd 76.8% | 3rd 76.8% | 8th 69.5% | 1st 77.8% | 17th 63.7% | 10th 67.8% | 14th 65.8% | 11th 67.5% | 17th 63.7% | 19th 63.0% | 15th 65.3% | 13th 66.0% | 9th 68.8% | 5th 71.5% | 4th 73.8% | 12th 66.3% | 6th 71.0% | 16th 64.3% | 20th 62.5% | 20th 62.5% | |
| 65.4% | 65% | 70% | 70% | 61% | 70% | 53% | 70% | 64% | 61% | 62% | 67% | 69% | 70% | 78% | 65% | 61% | 70% | 70% | 61% | 65% | 51% | |
| 76.0% | 72% | 84% | 84% | 72% | 88% | 78% | 74% | 69% | 78% | 72% | 72% | 84% | 78% | 78% | 75% | 78% | 69% | 83% | 78% | 67% | 63% | |
| 62.4% | 68% | 78% | 69% | 76% | 76% | 59% | 66% | 54% | 62% | 59% | 49% | 44% | 51% | 55% | 69% | 79% | 59% | 54% | 54% | 57% | 72% | |
| 69.4% | 75% | 75% | 84% | 69% | 77% | 65% | 61% | 76% | 69% | 62% | 64% | 64% | 65% | 64% | 77% | 77% | 67% | 77% | 64% | 61% | 64% |