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 Philippines. 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 | 1st 76.9% | 4th 68.2% | 6th 65.0% | 2nd 71.3% | 5th 66.3% | 3rd 71.1% | |
| 80.0% | 84% | 78% | 76% | 79% | 83% | 80% | |
| 48.2% | 48% | 47% | 35% | 48% | 58% | 53% | |
| 69.8% | 76% | 65% | 60% | 82% | 78% | 58% | |
| 83.0% | 93% | 82% | 84% | 92% | 65% | 82% | |
| 63.7% | 71% | 61% | 69% | 67% | 48% | 66% | |
| 75.0% | 82% | 74% | 68% | 71% | 83% | 72% | |
| 62.2% | 77% | 66% | 49% | 41% | 75% | 65% | |
| 57.5% | 64% | 66% | 59% | 57% | 38% | 61% | |
| 90.8% | 94% | 74% | 99% | 88% | 99% | ||
| 71.7% | 80% | 75% | 76% | 77% | 47% | 75% |