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 | 4th 74.3% | 6th 71.7% | 5th 72.4% | 2nd 75.3% | 1st 77.7% | 3rd 75.3% | |
| 86.7% | 89% | 84% | 84% | 87% | 89% | 87% | |
| 70.0% | 62% | 66% | 75% | 75% | 71% | 71% | |
| 84.8% | 91% | 86% | 79% | 86% | 81% | 86% | |
| 78.5% | 65% | 71% | 86% | 78% | 75% | 96% | |
| 74.8% | 85% | 81% | 60% | 82% | 78% | 63% | |
| 87.3% | 89% | 90% | 78% | 86% | 94% | 87% | |
| 45.2% | 33% | 22% | 75% | 26% | 60% | 55% | |
| 72.5% | 84% | 68% | 62% | 77% | 76% | 68% | |
| 65.0% | 60% | 70% | 59% | 71% | 67% | 63% | |
| 79.7% | 85% | 79% | 66% | 85% | 86% | 77% |