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 Vietnam. 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 | 2nd 77.8% | 3rd 76.8% | 6th 66.8% | 1st 79.3% | 4th 76.7% | 5th 75.7% | |
| 71.7% | 67% | 58% | 75% | 70% | 78% | 82% | |
| 78.2% | 86% | 78% | 54% | 92% | 81% | 78% | |
| 80.7% | 69% | 93% | 93% | 79% | 75% | 75% | |
| 67.3% | 62% | 54% | 69% | 76% | 71% | 72% | |
| 75.3% | 80% | 87% | 58% | 73% | 81% | 73% | |
| 73.2% | 82% | 80% | 52% | 76% | 77% | 72% | |
| 73.2% | 78% | 84% | 61% | 80% | 73% | 63% | |
| 73.8% | 77% | 70% | 63% | 83% | 72% | 78% | |
| 83.7% | 92% | 83% | 66% | 89% | 91% | 81% | |
| 78.2% | 85% | 81% | 77% | 75% | 68% | 83% |