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 Italy. 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 76.8% | 10th 70.0% | 9th 70.3% | 8th 73.5% | 11th 69.8% | 6th 74.3% | 6th 74.3% | 12th 67.8% | 3rd 76.5% | 13th 66.8% | 4th 76.0% | 5th 75.0% | 1st 78.5% | |
| 65.6% | 67% | 60% | 54% | 67% | 54% | 65% | 69% | 54% | 77% | 69% | 77% | 63% | 77% | |
| 84.1% | 88% | 77% | 79% | 83% | 86% | 87% | 81% | 84% | 89% | 73% | 86% | 91% | 89% | |
| 60.9% | 71% | 65% | 65% | 61% | 61% | 60% | 64% | 56% | 62% | 47% | 53% | 62% | 65% | |
| 81.5% | 81% | 78% | 83% | 83% | 78% | 85% | 83% | 77% | 78% | 78% | 88% | 84% | 83% |