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 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 | 1st 67.5% | 2nd 64.7% | 5th 59.1% | 3rd 61.8% | 6th 57.1% | 4th 60.7% | |
| 48.7% | 52% | 49% | 42% | 58% | 42% | 49% | |
| 52.8% | 56% | 59% | 47% | 47% | 58% | 50% | |
| 57.2% | 65% | 62% | 44% | 63% | 58% | 51% | |
| 59.7% | 78% | 84% | 45% | 67% | 26% | 58% | |
| 55.3% | 53% | 46% | 54% | 59% | 57% | 63% | |
| 70.0% | 77% | 76% | 76% | 65% | 56% | 70% | |
| 65.0% | 67% | 54% | 75% | 54% | 70% | 70% | |
| 78.7% | 85% | 83% | 79% | 80% | 65% | 80% | |
| 47.3% | 55% | 47% | 48% | 35% | 63% | 36% | |
| 83.5% | 87% | 87% | 81% | 90% | 76% | 80% |