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 Japan. Source: Global Dialogues GD4 (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 74.8% | 5th 70.7% | 4th 71.1% | 3rd 71.3% | 2nd 71.4% | 6th 69.7% | |
| 59.2% | 70% | 58% | 70% | 54% | 49% | 54% | |
| 69.5% | 74% | 69% | 67% | 74% | 69% | 64% | |
| 76.5% | 76% | 78% | 74% | 69% | 81% | 81% | |
| 77.8% | 74% | 75% | 73% | 80% | 88% | 77% | |
| 77.7% | 88% | 84% | 60% | 90% | 77% | 67% | |
| 66.0% | 65% | 67% | 74% | 68% | 54% | 68% | |
| 67.0% | 75% | 39% | 80% | 62% | 78% | 68% | |
| 64.8% | 71% | 74% | 62% | 68% | 54% | 60% | |
| 82.3% | 77% | 86% | 72% | 87% | 85% | 87% | |
| 74.2% | 78% | 77% | 79% | 61% | 79% | 71% |