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 Poland. 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 | 3rd 77.6% | 5th 73.9% | 4th 77.2% | 2nd 78.1% | 6th 70.8% | 1st 81.2% | |
| 87.7% | 96% | 91% | 84% | 76% | 96% | 83% | |
| 75.8% | 76% | 82% | 74% | 76% | 73% | 74% | |
| 82.3% | 84% | 67% | 92% | 75% | 90% | 86% | |
| 87.0% | 86% | 92% | 86% | 98% | 73% | 87% | |
| 69.2% | 73% | 62% | 77% | 72% | 54% | 77% | |
| 67.8% | 66% | 58% | 77% | 66% | 50% | 90% | |
| 70.3% | 57% | 67% | 67% | 83% | 71% | 77% | |
| 75.3% | 78% | 78% | 68% | 79% | 74% | 75% | |
| 63.8% | 68% | 50% | 68% | 77% | 42% | 78% | |
| 85.3% | 92% | 92% | 79% | 79% | 85% | 85% |