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 | 4th 69.2% | 1st 76.2% | 5th 68.8% | 3rd 70.3% | 6th 65.0% | 2nd 74.2% | |
| 69.5% | 67% | 69% | 79% | 71% | 54% | 77% | |
| 81.7% | 93% | 90% | 62% | 87% | 68% | 90% | |
| 73.2% | 75% | 72% | 79% | 76% | 61% | 76% | |
| 63.8% | 67% | 62% | 66% | 59% | 63% | 66% | |
| 65.5% | 63% | 87% | 62% | 54% | 53% | 74% | |
| 82.7% | 76% | 87% | 74% | 81% | 90% | 88% | |
| 58.2% | 58% | 55% | 60% | 59% | 53% | 64% | |
| 75.2% | 72% | 83% | 77% | 73% | 75% | 71% | |
| 71.5% | 62% | 90% | 68% | 82% | 56% | 71% | |
| 65.0% | 59% | 67% | 61% | 61% | 77% | 65% |