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 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 | 2nd 69.8% | 1st 73.2% | 5th 64.8% | 3rd 68.9% | 4th 66.3% | 6th 63.8% | |
| 77.8% | 80% | 77% | 78% | 73% | 73% | 86% | |
| 54.8% | 55% | 63% | 45% | 59% | 53% | 54% | |
| 64.5% | 67% | 74% | 59% | 63% | 67% | 57% | |
| 86.3% | 82% | 89% | 96% | 89% | 78% | 84% | |
| 70.3% | 71% | 66% | 72% | 73% | 73% | 67% | |
| 67.3% | 69% | 79% | 59% | 72% | 66% | 59% | |
| 69.0% | 76% | 80% | 79% | 59% | 59% | 61% | |
| 72.2% | 71% | 69% | 69% | 80% | 73% | 71% | |
| 59.2% | 60% | 76% | 31% | 71% | 62% | 55% | |
| 56.5% | 67% | 59% | 60% | 50% | 59% | 44% |