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 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 75.0% | 5th 70.3% | 6th 68.9% | 1st 77.0% | 3rd 73.3% | 4th 73.1% | |
| 71.2% | 76% | 75% | 70% | 66% | 70% | 70% | |
| 80.3% | 84% | 80% | 83% | 88% | 62% | 85% | |
| 77.0% | 81% | 72% | 62% | 88% | 81% | 78% | |
| 71.2% | 61% | 61% | 66% | 88% | 78% | 73% | |
| 68.3% | 76% | 62% | 53% | 69% | 75% | 75% | |
| 64.5% | 66% | 61% | 70% | 64% | 60% | 66% | |
| 83.8% | 84% | 75% | 80% | 87% | 90% | 87% | |
| 77.8% | 78% | 80% | 82% | 80% | 82% | 65% | |
| 66.5% | 72% | 61% | 54% | 65% | 75% | 72% | |
| 68.7% | 72% | 76% | 69% | 75% | 60% | 60% |