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 | 2nd 55.2% | 6th 52.2% | 1st 56.4% | 3rd 54.7% | 5th 52.6% | 4th 54.1% | |
| 40.0% | 43% | 32% | 35% | 40% | 46% | 44% | |
| 62.7% | 61% | 58% | 73% | 61% | 60% | 63% | |
| 71.3% | 77% | 70% | 69% | 75% | 66% | 71% | |
| 58.5% | 45% | 51% | 82% | 63% | 47% | 63% | |
| 28.8% | 49% | 22% | 13% | 28% | 33% | 28% | |
| 63.0% | 60% | 65% | 68% | 68% | 52% | 65% | |
| 65.2% | 63% | 65% | 77% | 63% | 58% | 65% | |
| 45.5% | 46% | 48% | 48% | 43% | 50% | 38% | |
| 45.7% | 48% | 51% | 40% | 44% | 47% | 44% | |
| 61.3% | 60% | 60% | 59% | 62% | 67% | 60% |