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 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 | 2nd 75.4% | 3rd 74.4% | 6th 69.9% | 4th 72.9% | 5th 70.6% | 1st 75.9% | |
| 81.0% | 82% | 78% | 86% | 78% | 80% | 82% | |
| 80.5% | 86% | 86% | 72% | 79% | 74% | 86% | |
| 65.3% | 69% | 70% | 64% | 62% | 58% | 69% | |
| 80.7% | 84% | 72% | 70% | 90% | 84% | 84% | |
| 72.0% | 77% | 71% | 75% | 63% | 76% | 70% | |
| 70.2% | 75% | 79% | 69% | 74% | 52% | 72% | |
| 73.2% | 71% | 65% | 71% | 71% | 86% | 75% | |
| 67.0% | 70% | 77% | 61% | 68% | 65% | 61% | |
| 72.5% | 69% | 75% | 65% | 63% | 84% | 79% | |
| 69.5% | 71% | 71% | 66% | 81% | 47% | 81% |