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 GD6 (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 | Gemini 2.5 Flash | Gemma 3 12b It | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | |
|---|---|---|---|---|---|---|---|
| Score | 3rd 67.6% | 1st 69.3% | 2nd 67.9% | 5th 67.1% | 6th 58.4% | 4th 67.3% | |
| 60.0% | 56% | 67% | 63% | 57% | 57% | ||
| 69.7% | 75% | 74% | 71% | 68% | 68% | 62% | |
| 62.5% | 66% | 71% | 60% | 59% | 47% | 72% | |
| 54.3% | 60% | 47% | 49% | 60% | 50% | 60% | |
| 54.5% | 56% | 58% | 51% | 48% | 64% | 50% | |
| 73.5% | 66% | 85% | 78% | 79% | 49% | 84% | |
| 75.8% | 77% | 88% | 76% | 70% | 68% | 76% | |
| 75.3% | 82% | 70% | 80% | 82% | 73% | 65% | |
| 65.0% | 57% | 60% | 75% | 62% | 62% | 74% | |
| 70.7% | 81% | 73% | 71% | 80% | 46% | 73% |