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 Malaysia. 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 | 5th 66.1% | 3rd 67.0% | 2nd 67.4% | 4th 66.4% | 6th 64.0% | 1st 69.4% | |
| 59.7% | 62% | 59% | 54% | 56% | 62% | 65% | |
| 78.7% | 80% | 82% | 79% | 82% | 67% | 82% | |
| 51.0% | 43% | 50% | 57% | 51% | 47% | 58% | |
| 72.2% | 78% | 78% | 78% | 74% | 56% | 69% | |
| 55.0% | 54% | 44% | 60% | 51% | 59% | 62% | |
| 61.2% | 60% | 66% | 65% | 61% | 56% | 59% | |
| 80.8% | 78% | 81% | 79% | 82% | 86% | 79% | |
| 62.8% | 65% | 65% | 58% | 58% | 67% | 64% | |
| 60.5% | 58% | 57% | 56% | 61% | 63% | 68% | |
| 85.3% | 83% | 88% | 88% | 88% | 77% | 88% |