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 GD6 (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 53.5% | 6th 48.0% | 5th 51.5% | 2nd 54.8% | 1st 55.4% | 3rd 54.0% | |
| 38.2% | 45% | 38% | 29% | 40% | 35% | 42% | |
| 61.5% | 56% | 59% | 67% | 61% | 57% | 69% | |
| 73.5% | 76% | 75% | 71% | 75% | 73% | 71% | |
| 59.2% | 52% | 51% | 52% | 73% | 67% | 60% | |
| 29.3% | 47% | 22% | 13% | 29% | 37% | 28% | |
| 64.8% | 62% | 65% | 71% | 63% | 63% | 65% | |
| 61.3% | 52% | 67% | 71% | 56% | 61% | 61% | |
| 43.7% | 39% | 50% | 42% | 43% | 46% | 42% | |
| 36.5% | 46% | 0% | 40% | 47% | 45% | 41% | |
| 60.7% | 60% | 53% | 59% | 61% | 70% | 61% |