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 Mexico. 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 | 8th 72.8% | 9th 72.0% | 6th 74.8% | 2nd 76.5% | 13th 65.5% | 4th 75.8% | 12th 66.5% | 10th 71.3% | 1st 77.0% | 5th 75.3% | 3rd 76.0% | 7th 74.5% | 11th 71.0% | |
| 67.8% | 65% | 65% | 60% | 67% | 57% | 66% | 69% | 74% | 76% | 76% | 77% | 64% | 65% | |
| 76.6% | 78% | 77% | 84% | 75% | 69% | 80% | 67% | 76% | 82% | 76% | 71% | 84% | 77% | |
| 65.6% | 68% | 72% | 73% | 71% | 57% | 65% | 59% | 64% | 68% | 51% | 65% | 68% | 72% | |
| 81.9% | 80% | 74% | 82% | 93% | 79% | 92% | 71% | 71% | 82% | 98% | 91% | 82% | 70% |