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 Egypt. 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 | 1st 76.1% | 5th 71.8% | 3rd 73.4% | 2nd 74.2% | 6th 71.6% | 4th 72.6% | |
| 74.2% | 76% | 73% | 75% | 75% | 72% | 74% | |
| 61.8% | 67% | 58% | 67% | 61% | 60% | 58% | |
| 82.5% | 77% | 89% | 74% | 83% | 90% | 82% | |
| 82.3% | 83% | 87% | 85% | 80% | 81% | 78% | |
| 63.3% | 62% | 68% | 60% | 55% | 62% | 73% | |
| 83.7% | 91% | 81% | 85% | 79% | 81% | 85% | |
| 64.7% | 66% | 67% | 63% | 75% | 58% | 59% | |
| 53.8% | 63% | 38% | 61% | 65% | 47% | 49% | |
| 85.7% | 87% | 84% | 86% | 82% | 90% | 85% | |
| 80.8% | 89% | 73% | 78% | 87% | 75% | 83% |