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 Rural. 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 | 3rd 77.4% | 1st 83.0% | 6th 68.2% | 4th 77.0% | 2nd 79.5% | 5th 76.3% | |
| 86.3% | 88% | 90% | 80% | 89% | 83% | 88% | |
| 71.9% | 75% | 74% | 62% | 74% | 76% | 71% | |
| 85.4% | 85% | 91% | 86% | 88% | 77% | 86% | |
| 86.4% | 86% | 94% | 81% | 77% | 90% | 92% | |
| 77.0% | 79% | 86% | 74% | 74% | 87% | 63% | |
| 85.0% | 87% | 89% | 78% | 85% | 85% | 86% | |
| 55.5% | 49% | 64% | 51% | 56% | 55% | 58% | |
| 72.2% | 78% | 71% | 58% | 75% | 77% | 74% | |
| 71.9% | 67% | 86% | 60% | 72% | 76% | 71% | |
| 77.3% | 81% | 85% | 52% | 82% | 90% | 74% |