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 Islam. 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 Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | Qwen3 30b A3B Instruct 2507 | Qwen3 Next 80b A3B Instruct | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 86.3% | 7th 83.0% | 4th 85.5% | 9th 81.0% | 13th 78.3% | 10th 80.5% | 8th 82.5% | 3rd 85.8% | 6th 83.8% | 12th 78.5% | 11th 80.3% | 1st 86.8% | 5th 85.0% | |
| 72.2% | 72% | 63% | 70% | 74% | 59% | 70% | 66% | 73% | 82% | 78% | 84% | 73% | 74% | |
| 85.8% | 86% | 90% | 92% | 85% | 83% | 89% | 88% | 93% | 87% | 67% | 80% | 86% | 90% | |
| 86.8% | 94% | 89% | 96% | 82% | 78% | 92% | 90% | 79% | 78% | 80% | 95% | 89% | ||
| 86.8% | 93% | 96% | 91% | 69% | 89% | 85% | 84% | 87% | 87% | 91% | 77% | 93% | 87% |