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 75.3% | 6th 54.5% | 4th 74.6% | 5th 73.0% | 3rd 74.7% | 1st 77.4% | |
| 63.3% | 67% | 44% | 86% | 55% | 60% | 68% | |
| 86.2% | 93% | 90% | 76% | 91% | 86% | 81% | |
| 68.2% | 65% | 60% | 69% | 60% | 79% | 76% | |
| 63.8% | 74% | 55% | 65% | 71% | 55% | 63% | |
| 75.5% | 76% | 64% | 66% | 84% | 86% | 77% | |
| 81.2% | 70% | 77% | 89% | 94% | 68% | 89% | |
| 55.7% | 61% | 0% | 74% | 52% | 61% | 86% | |
| 74.0% | 76% | 74% | 81% | 61% | 77% | 75% | |
| 78.3% | 82% | 81% | 74% | 76% | 81% | 76% | |
| 69.7% | 89% | 0% | 66% | 86% | 94% | 83% |