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 77.3% | 6th 69.5% | 5th 71.6% | 4th 75.5% | 3rd 75.5% | 1st 77.7% | |
| 64.2% | 76% | 45% | 73% | 60% | 65% | 66% | |
| 90.3% | 93% | 92% | 91% | 92% | 89% | 85% | |
| 69.2% | 68% | 57% | 61% | 69% | 79% | 81% | |
| 65.5% | 65% | 64% | 53% | 70% | 78% | 63% | |
| 77.2% | 84% | 71% | 57% | 90% | 78% | 83% | |
| 84.8% | 80% | 91% | 89% | 85% | 73% | 91% | |
| 59.8% | 56% | 38% | 78% | 52% | 61% | 74% | |
| 72.3% | 78% | 71% | 74% | 69% | 67% | 75% | |
| 78.2% | 82% | 82% | 74% | 76% | 79% | 76% | |
| 83.7% | 91% | 84% | 66% | 92% | 86% | 83% |