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 Indonesia. Source: Global Dialogues GD4 (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 70.1% | 5th 67.2% | 6th 67.1% | 3rd 69.4% | 2nd 70.0% | 4th 67.6% | |
| 74.8% | 69% | 75% | 74% | 78% | 78% | 75% | |
| 71.0% | 77% | 74% | 61% | 74% | 74% | 66% | |
| 80.8% | 77% | 78% | 88% | 83% | 84% | 75% | |
| 64.2% | 64% | 47% | 80% | 66% | 64% | 64% | |
| 75.0% | 76% | 77% | 72% | 77% | 73% | 75% | |
| 75.0% | 75% | 76% | 75% | 76% | 78% | 70% | |
| 46.2% | 44% | 22% | 62% | 36% | 50% | 63% | |
| 69.3% | 82% | 82% | 53% | 79% | 60% | 60% | |
| 56.7% | 62% | 55% | 51% | 56% | 60% | 56% | |
| 72.7% | 75% | 86% | 55% | 69% | 79% | 72% |