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 | 1st 67.5% | 2nd 67.4% | 4th 62.6% | 3rd 65.3% | 5th 60.7% | 5th 60.7% | |
| 76.3% | 75% | 82% | 70% | 76% | 77% | 78% | |
| 58.2% | 60% | 67% | 59% | 56% | 51% | 56% | |
| 65.2% | 63% | 70% | 66% | 68% | 60% | 64% | |
| 70.3% | 85% | 65% | 55% | 88% | 54% | 75% | |
| 57.3% | 58% | 53% | 55% | 57% | 64% | 57% | |
| 68.2% | 77% | 75% | 68% | 66% | 56% | 67% | |
| 61.3% | 65% | 71% | 65% | 52% | 64% | 51% | |
| 73.5% | 77% | 76% | 74% | 77% | 65% | 72% | |
| 61.5% | 63% | 60% | 63% | 67% | 68% | 48% | |
| 48.5% | 52% | 55% | 51% | 46% | 48% | 39% |