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 | 1st 76.5% | 5th 71.0% | 6th 64.0% | 2nd 74.2% | 4th 72.0% | 3rd 73.5% | |
| 63.2% | 69% | 64% | 58% | 63% | 68% | 57% | |
| 65.5% | 79% | 70% | 54% | 81% | 52% | 57% | |
| 84.8% | 92% | 79% | 66% | 88% | 92% | 92% | |
| 56.7% | 55% | 45% | 55% | 62% | 63% | 60% | |
| 75.0% | 84% | 73% | 50% | 75% | 80% | 88% | |
| 73.8% | 75% | 78% | 75% | 77% | 64% | 74% | |
| 67.8% | 71% | 69% | 68% | 70% | 61% | 68% | |
| 70.5% | 70% | 73% | 67% | 68% | 68% | 77% | |
| 79.7% | 87% | 81% | 73% | 73% | 88% | 76% | |
| 81.7% | 83% | 78% | 74% | 85% | 84% | 86% |