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 Chile. Source: Global Dialogues GD4 (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 | 2nd 73.5% | 1st 73.6% | 4th 72.6% | 5th 72.4% | 6th 65.0% | 3rd 73.5% | |
| 75.8% | 76% | 78% | 76% | 81% | 65% | 80% | |
| 85.5% | 84% | 88% | 82% | 85% | 87% | 87% | |
| 78.0% | 82% | 72% | 82% | 76% | 67% | 90% | |
| 67.5% | 75% | 70% | 61% | 61% | 69% | 69% | |
| 86.3% | 87% | 83% | 77% | 93% | 95% | 83% | |
| 72.4% | 76% | 75% | 86% | 80% | 48% | 71% | |
| 23.6% | 21% | 36% | 18% | 21% | 22% | 24% | |
| 76.7% | 78% | 78% | 76% | 80% | 68% | 81% | |
| 81.7% | 81% | 83% | 86% | 81% | 79% | 81% | |
| 70.1% | 76% | 74% | 83% | 68% | 50% | 70% |