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 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 77.9% | 4th 74.5% | 5th 70.4% | 2nd 77.0% | 6th 69.6% | 3rd 76.4% | |
| 78.3% | 82% | 80% | 59% | 82% | 84% | 83% | |
| 78.7% | 73% | 83% | 80% | 85% | 71% | 80% | |
| 76.7% | 80% | 78% | 79% | 77% | 73% | 73% | |
| 65.0% | 66% | 65% | 67% | 69% | 53% | 70% | |
| 76.0% | 82% | 69% | 60% | 84% | 77% | 84% | |
| 71.5% | 78% | 78% | 62% | 70% | 71% | 70% | |
| 67.5% | 64% | 41% | 87% | 69% | 61% | 83% | |
| 77.2% | 82% | 84% | 62% | 81% | 78% | 76% | |
| 77.5% | 88% | 86% | 63% | 78% | 76% | 74% | |
| 74.7% | 84% | 81% | 85% | 75% | 52% | 71% |