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 Slovakia. 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 67.1% | 1st 71.9% | 5th 61.1% | 2nd 67.5% | 4th 62.5% | 6th 59.5% | |
| 74.2% | 73% | 78% | 61% | 76% | 81% | 76% | |
| 48.8% | 52% | 52% | 45% | 45% | 48% | 51% | |
| 63.7% | 65% | 71% | 56% | 67% | 58% | 65% | |
| 63.3% | 73% | 81% | 45% | 83% | 42% | 56% | |
| 69.8% | 65% | 69% | 68% | 70% | 73% | 74% | |
| 71.2% | 62% | 77% | 73% | 76% | 76% | 63% | |
| 91.8% | 89% | 100% | 100% | 83% | 90% | 89% | |
| 54.8% | 61% | 67% | 53% | 56% | 39% | 53% | |
| 59.5% | 67% | 66% | 59% | 60% | 74% | 31% | |
| 52.2% | 64% | 58% | 51% | 59% | 44% | 37% |