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 | 5th 74.8% | 11th 69.8% | 11th 69.8% | 6th 73.3% | 9th 72.3% | 7th 72.5% | 7th 72.5% | 10th 71.5% | 1st 80.5% | 13th 68.0% | 3rd 77.5% | 2nd 78.5% | 4th 76.8% | |
| 66.5% | 67% | 54% | 54% | 63% | 53% | 65% | 70% | 60% | 83% | 69% | 77% | 72% | 77% | |
| 84.0% | 90% | 83% | 83% | 77% | 96% | 81% | 75% | 78% | 91% | 73% | 90% | 87% | 88% | |
| 62.7% | 65% | 65% | 65% | 65% | 63% | 56% | 62% | 65% | 65% | 47% | 60% | 72% | 65% | |
| 81.5% | 77% | 77% | 77% | 88% | 77% | 88% | 83% | 83% | 83% | 83% | 83% | 83% | 77% |