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 GD7 (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% | 6th 68.3% | 3rd 72.9% | 5th 72.3% | 2nd 75.7% | 4th 72.6% | |
| 75.5% | 76% | 71% | 85% | 66% | 82% | 73% | |
| 69.7% | 66% | 76% | 58% | 73% | 77% | 68% | |
| 77.8% | 84% | 80% | 70% | 77% | 82% | 74% | |
| 76.3% | 75% | 73% | 75% | 81% | 72% | 82% | |
| 78.7% | 83% | 89% | 56% | 81% | 86% | 77% | |
| 75.0% | 86% | 76% | 69% | 68% | 79% | 72% | |
| 56.0% | 77% | 0% | 75% | 59% | 55% | 70% | |
| 69.2% | 61% | 60% | 85% | 60% | 78% | 71% | |
| 79.0% | 81% | 87% | 82% | 82% | 77% | 65% | |
| 73.3% | 76% | 71% | 74% | 76% | 69% | 74% |