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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 15th 78.0% | 2nd 84.0% | 16th 77.3% | 12th 80.3% | 19th 75.5% | 20th 74.5% | 4th 83.0% | 13th 78.5% | 18th 76.3% | 14th 78.3% | 7th 82.0% | 21st 66.0% | 7th 82.0% | 10th 80.8% | 17th 76.5% | 4th 83.0% | 11th 80.5% | 4th 83.0% | 3rd 83.8% | 9th 81.8% | 1st 86.5% | |
| 72.0% | 70% | 69% | 61% | 70% | 66% | 57% | 67% | 74% | 65% | 63% | 81% | 69% | 75% | 85% | 77% | 73% | 77% | 80% | 81% | 75% | 77% | |
| 85.5% | 78% | 97% | 78% | 88% | 74% | 82% | 97% | 88% | 78% | 88% | 92% | 59% | 98% | 90% | 83% | 93% | 93% | 82% | 91% | 83% | 83% | |
| 79.0% | 80% | 90% | 87% | 80% | 86% | 76% | 85% | 76% | 79% | 78% | 72% | 53% | 72% | 71% | 63% | 83% | 69% | 94% | 80% | 92% | 92% | |
| 81.9% | 84% | 80% | 83% | 83% | 76% | 83% | 83% | 76% | 83% | 84% | 83% | 83% | 83% | 77% | 83% | 83% | 83% | 76% | 83% | 77% | 94% |