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 Kazakhstan. Source: Global Dialogues GD4 (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 67.0% | 5th 65.0% | 3rd 67.3% | 2nd 69.2% | 6th 61.1% | 1st 70.3% | |
| 61.8% | 53% | 53% | 74% | 71% | 49% | 71% | |
| 80.0% | 88% | 82% | 66% | 88% | 74% | 83% | |
| 74.5% | 75% | 67% | 72% | 80% | 74% | 79% | |
| 74.7% | 83% | 74% | 57% | 68% | 84% | 83% | |
| 65.9% | 69% | 67% | 66% | 70% | 64% | 60% | |
| 62.6% | 66% | 59% | 81% | 71% | 39% | 60% | |
| 45.0% | 37% | 53% | 41% | 37% | 49% | 53% | |
| 58.6% | 50% | 54% | 71% | 61% | 50% | 66% | |
| 83.3% | 84% | 87% | 70% | 85% | 86% | 89% | |
| 60.1% | 66% | 54% | 75% | 62% | 43% | 61% |