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 Türkiye. 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 | 4th 57.8% | 3rd 58.9% | 5th 56.7% | 2nd 59.1% | 1st 59.6% | 6th 56.3% | |
| 72.7% | 74% | 76% | 82% | 75% | 58% | 71% | |
| 73.8% | 79% | 73% | 64% | 77% | 84% | 66% | |
| 42.0% | 42% | 45% | 38% | 40% | 47% | 40% | |
| 68.7% | 67% | 69% | 76% | 69% | 66% | 65% | |
| 60.7% | 55% | 56% | 68% | 62% | 57% | 66% | |
| 50.3% | 57% | 60% | 37% | 50% | 51% | 47% | |
| 49.7% | 49% | 46% | 47% | 47% | 58% | 51% | |
| 59.7% | 63% | 60% | 58% | 64% | 57% | 56% | |
| 56.8% | 54% | 62% | 48% | 59% | 65% | 53% | |
| 46.3% | 38% | 42% | 49% | 48% | 53% | 48% |