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 China. 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 | 2nd 81.6% | 1st 82.2% | 6th 75.4% | 3rd 80.5% | 5th 78.2% | 4th 78.6% | |
| 74.8% | 77% | 70% | 76% | 64% | 86% | 76% | |
| 76.2% | 84% | 77% | 58% | 91% | 60% | 87% | |
| 82.8% | 87% | 83% | 78% | 88% | 79% | 82% | |
| 77.8% | 82% | 68% | 78% | 80% | 87% | 72% | |
| 72.2% | 66% | 81% | 69% | 74% | 79% | 64% | |
| 82.7% | 95% | 82% | 84% | 85% | 69% | 81% | |
| 82.8% | 90% | 92% | 78% | 83% | 66% | 88% | |
| 78.2% | 69% | 84% | 74% | 75% | 86% | 81% | |
| 84.0% | 80% | 93% | 77% | 84% | 89% | 81% | |
| 82.7% | 86% | 92% | 82% | 81% | 81% | 74% |