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 | 3rd 78.0% | 2nd 78.5% | 6th 65.3% | 1st 79.2% | 4th 77.7% | 5th 74.5% | |
| 75.0% | 66% | 68% | 78% | 72% | 84% | 82% | |
| 78.7% | 86% | 78% | 54% | 97% | 83% | 74% | |
| 82.7% | 70% | 93% | 89% | 80% | 84% | 80% | |
| 69.8% | 67% | 65% | 76% | 76% | 63% | 72% | |
| 72.3% | 83% | 88% | 52% | 64% | 74% | 73% | |
| 76.8% | 82% | 86% | 56% | 81% | 85% | 71% | |
| 74.3% | 84% | 79% | 49% | 85% | 87% | 62% | |
| 73.3% | 73% | 68% | 66% | 77% | 73% | 83% | |
| 82.3% | 89% | 83% | 66% | 88% | 87% | 81% | |
| 70.0% | 80% | 77% | 67% | 72% | 57% | 67% |