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 GD3 (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 71.2% | 1st 75.6% | 4th 69.2% | 5th 67.3% | 6th 66.2% | 2nd 73.9% | |
| 73.8% | 70% | 75% | 82% | 73% | 64% | 79% | |
| 79.3% | 93% | 95% | 63% | 70% | 68% | 87% | |
| 71.7% | 75% | 71% | 79% | 66% | 63% | 76% | |
| 62.7% | 67% | 53% | 65% | 61% | 63% | 67% | |
| 65.0% | 66% | 83% | 63% | 54% | 53% | 71% | |
| 80.3% | 76% | 84% | 78% | 74% | 84% | 86% | |
| 58.3% | 58% | 55% | 60% | 58% | 53% | 66% | |
| 78.3% | 83% | 83% | 78% | 76% | 79% | 71% | |
| 72.0% | 65% | 90% | 68% | 82% | 56% | 71% | |
| 64.2% | 59% | 67% | 56% | 59% | 79% | 65% |