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 78.3% | 3rd 84.5% | 16th 77.5% | 13th 80.3% | 19th 75.8% | 18th 76.3% | 8th 83.0% | 19th 75.8% | 17th 77.0% | 11th 80.8% | 7th 83.5% | 21st 62.2% | 14th 79.2% | 11th 80.8% | 2nd 86.5% | 9th 82.5% | 5th 83.8% | 4th 84.0% | 9th 82.5% | 1st 89.8% | 6th 83.8% | |
| 72.3% | 70% | 69% | 65% | 70% | 66% | 55% | 67% | 74% | 68% | 68% | 78% | 54% | 78% | 85% | 81% | 73% | 80% | 83% | 77% | 80% | 77% | |
| 86.6% | 74% | 97% | 75% | 88% | 79% | 87% | 97% | 77% | 78% | 88% | 97% | 59% | 85% | 90% | 97% | 93% | 92% | 95% | 91% | 96% | 83% | |
| 80.2% | 85% | 90% | 87% | 80% | 86% | 80% | 85% | 76% | 79% | 85% | 76% | 53% | 72% | 71% | 85% | 81% | 80% | 74% | 79% | 89% | 92% | |
| 82.3% | 84% | 82% | 83% | 83% | 72% | 83% | 83% | 76% | 83% | 82% | 83% | 83% | 82% | 77% | 83% | 83% | 83% | 84% | 83% | 94% | 83% |