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 | 6th 72.9% | 2nd 78.0% | 5th 74.5% | 3rd 76.6% | 3rd 76.6% | 1st 78.4% | |
| 64.5% | 56% | 46% | 82% | 55% | 75% | 73% | |
| 81.7% | 93% | 88% | 61% | 85% | 77% | 86% | |
| 79.0% | 80% | 74% | 82% | 79% | 75% | 84% | |
| 79.2% | 59% | 80% | 82% | 84% | 85% | 85% | |
| 76.2% | 70% | 85% | 76% | 79% | 82% | 65% | |
| 80.0% | 67% | 88% | 88% | 82% | 63% | 92% | |
| 67.3% | 59% | 82% | 61% | 61% | 75% | 66% | |
| 73.5% | 74% | 73% | 73% | 78% | 72% | 71% | |
| 77.8% | 84% | 73% | 75% | 79% | 78% | 78% | |
| 82.5% | 87% | 91% | 65% | 84% | 84% | 84% |