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 Pakistan. Source: Global Dialogues GD7 (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 73.0% | 1st 74.8% | 6th 64.5% | 2nd 73.9% | 5th 72.3% | 4th 72.4% | |
| 68.8% | 71% | 69% | 74% | 69% | 60% | 70% | |
| 66.8% | 71% | 67% | 49% | 71% | 74% | 69% | |
| 88.2% | 93% | 88% | 67% | 94% | 95% | 92% | |
| 64.8% | 67% | 65% | 71% | 66% | 55% | 65% | |
| 74.7% | 80% | 84% | 59% | 75% | 75% | 75% | |
| 81.8% | 87% | 84% | 68% | 84% | 86% | 82% | |
| 66.2% | 70% | 72% | 58% | 65% | 69% | 63% | |
| 71.8% | 76% | 76% | 57% | 72% | 74% | 76% | |
| 71.3% | 55% | 79% | 81% | 70% | 72% | 71% | |
| 63.7% | 60% | 64% | 61% | 73% | 63% | 61% |