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 Vietnam. 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 | 1st 73.5% | 2nd 69.7% | 6th 59.0% | 4th 68.6% | 5th 64.1% | 3rd 68.6% | |
| 67.4% | 70% | 74% | 65% | 55% | 73% | ||
| 68.3% | 77% | 72% | 59% | 61% | 74% | 67% | |
| 65.8% | 59% | 69% | 69% | 78% | 54% | ||
| 47.6% | 53% | 41% | 53% | 38% | 53% | ||
| 71.8% | 79% | 63% | 73% | 67% | 77% | ||
| 74.0% | 81% | 70% | 73% | 68% | 78% | ||
| 78.2% | 91% | 92% | 73% | 74% | 61% | ||
| 75.4% | 86% | 68% | 78% | 69% | 76% | ||
| 74.8% | 74% | 85% | 73% | 65% | 77% | ||
| 63.8% | 65% | 63% | 68% | 53% | 70% |