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 Mexico. Source: Global Dialogues GD5 (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 73.6% | 4th 72.1% | 2nd 75.1% | 6th 70.9% | 5th 71.6% | 1st 76.8% | |
| 65.3% | 72% | 69% | 68% | 60% | 63% | 60% | |
| 73.7% | 71% | 77% | 79% | 75% | 69% | 71% | |
| 73.5% | 73% | 71% | 78% | 64% | 74% | 81% | |
| 82.0% | 87% | 90% | 78% | 82% | 64% | 91% | |
| 58.0% | 68% | 47% | 62% | 53% | 59% | 59% | |
| 72.0% | 63% | 65% | 76% | 72% | 80% | 76% | |
| 84.7% | 83% | 72% | 73% | 86% | 99% | 95% | |
| 73.8% | 66% | 82% | 81% | 75% | 64% | 75% | |
| 72.0% | 78% | 66% | 76% | 62% | 78% | ||
| 80.2% | 75% | 82% | 80% | 82% | 82% |