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 GD3 (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 | 1st 82.3% | 2nd 81.2% | 5th 77.6% | 4th 77.9% | 6th 74.9% | 3rd 80.8% | |
| 85.2% | 88% | 92% | 85% | 77% | 86% | 83% | |
| 66.0% | 67% | 76% | 67% | 68% | 47% | 71% | |
| 77.5% | 83% | 80% | 69% | 70% | 87% | 76% | |
| 88.0% | 93% | 85% | 94% | 85% | 84% | 87% | |
| 61.2% | 65% | 71% | 52% | 66% | 52% | 61% | |
| 83.3% | 80% | 90% | 91% | 83% | 66% | 90% | |
| 86.3% | 89% | 88% | 87% | 84% | 85% | 85% | |
| 89.3% | 91% | 91% | 88% | 91% | 84% | 91% | |
| 72.7% | 79% | 57% | 69% | 68% | 85% | 78% | |
| 81.7% | 88% | 82% | 74% | 87% | 73% | 86% |