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 Kenya. Source: Global Dialogues GD6 (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 | 2nd 76.8% | 3rd 74.9% | 6th 64.3% | 4th 73.6% | 1st 77.6% | 5th 73.3% | |
| 60.3% | 64% | 63% | 60% | 56% | 65% | 54% | |
| 76.3% | 82% | 78% | 80% | 74% | 62% | 82% | |
| 79.2% | 84% | 82% | 63% | 81% | 83% | 82% | |
| 73.8% | 74% | 66% | 66% | 72% | 98% | 67% | |
| 71.0% | 83% | 62% | 54% | 69% | 76% | 82% | |
| 78.7% | 88% | 83% | 62% | 78% | 91% | 70% | |
| 84.7% | 81% | 87% | 78% | 90% | 90% | 82% | |
| 72.7% | 74% | 75% | 62% | 77% | 74% | 74% | |
| 67.2% | 73% | 71% | 52% | 69% | 71% | 67% | |
| 69.8% | 65% | 82% | 66% | 70% | 66% |