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 57.7% | 5th 57.6% | 1st 60.4% | 3rd 57.7% | 6th 55.1% | 2nd 59.6% | |
| 67.8% | 70% | 62% | 64% | 72% | 64% | 75% | |
| 75.2% | 73% | 71% | 82% | 77% | 71% | 77% | |
| 43.3% | 39% | 46% | 31% | 44% | 46% | 54% | |
| 64.5% | 64% | 64% | 66% | 63% | 65% | 65% | |
| 60.3% | 61% | 60% | 64% | 58% | 61% | 58% | |
| 54.0% | 60% | 58% | 50% | 54% | 52% | 50% | |
| 50.5% | 54% | 47% | 58% | 46% | 47% | 51% | |
| 62.2% | 63% | 57% | 75% | 64% | 50% | 64% | |
| 55.7% | 47% | 60% | 63% | 58% | 52% | 54% | |
| 46.7% | 46% | 51% | 51% | 41% | 43% | 48% |