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 Korea South. 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 | 3rd 72.7% | 1st 73.2% | 4th 68.8% | 5th 68.1% | 6th 65.5% | 2nd 72.7% | |
| 60.3% | 54% | 66% | 50% | 65% | 62% | 65% | |
| 64.7% | 83% | 72% | 55% | 53% | 61% | 64% | |
| 77.3% | 79% | 72% | 81% | 68% | 84% | 80% | |
| 56.7% | 60% | 53% | 54% | 58% | 59% | 56% | |
| 79.5% | 82% | 79% | 80% | 78% | 73% | 85% | |
| 78.7% | 76% | 77% | 80% | 81% | 70% | 88% | |
| 62.7% | 66% | 68% | 61% | 65% | 52% | 64% | |
| 59.5% | 63% | 68% | 62% | 56% | 51% | 57% | |
| 80.0% | 88% | 90% | 80% | 72% | 68% | 82% | |
| 82.3% | 76% | 87% | 85% | 85% | 75% | 86% |