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 GD5 (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 78.1% | 1st 82.3% | 6th 72.3% | 2nd 81.6% | 5th 75.6% | 3rd 78.7% | |
| 66.2% | 68% | 69% | 40% | 73% | 79% | 68% | |
| 85.7% | 85% | 90% | 82% | 86% | 84% | 87% | |
| 84.2% | 88% | 90% | 74% | 91% | 84% | 78% | |
| 82.8% | 95% | 92% | 75% | 95% | 51% | 89% | |
| 77.5% | 76% | 71% | 78% | 71% | 86% | 83% | |
| 81.8% | 77% | 83% | 87% | 79% | 82% | 83% | |
| 76.5% | 75% | 78% | 77% | 77% | 82% | 70% | |
| 76.8% | 71% | 82% | 70% | 85% | 76% | 77% | |
| 68.7% | 72% | 87% | 64% | 70% | 42% | 77% | |
| 80.8% | 74% | 81% | 76% | 89% | 90% | 75% |