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 Morocco. 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 | 2nd 72.6% | 4th 66.8% | 5th 62.8% | 1st 73.7% | 6th 61.0% | 3rd 67.9% | |
| 67.7% | 65% | 70% | 54% | 77% | 63% | 77% | |
| 75.3% | 82% | 73% | 89% | 79% | 56% | 73% | |
| 77.2% | 79% | 80% | 65% | 82% | 80% | 77% | |
| 58.3% | 80% | 75% | 39% | 75% | 24% | 57% | |
| 56.2% | 50% | 20% | 58% | 65% | 73% | 71% | |
| 70.2% | 78% | 75% | 66% | 70% | 68% | 64% | |
| 76.3% | 77% | 84% | 61% | 79% | 78% | 79% | |
| 60.8% | 62% | 63% | 65% | 70% | 42% | 63% | |
| 68.8% | 77% | 65% | 63% | 72% | 76% | 60% | |
| 63.8% | 76% | 63% | 68% | 68% | 50% | 58% |