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 56.1% | 6th 54.0% | 3rd 55.9% | 5th 54.0% | 4th 55.0% | 1st 56.9% | |
| 43.3% | 41% | 44% | 28% | 40% | 52% | 55% | |
| 68.8% | 66% | 65% | 81% | 64% | 69% | 68% | |
| 71.8% | 72% | 70% | 75% | 73% | 70% | 71% | |
| 64.8% | 59% | 54% | 74% | 67% | 63% | 72% | |
| 32.2% | 43% | 17% | 17% | 29% | 47% | 40% | |
| 64.2% | 66% | 72% | 68% | 65% | 53% | 61% | |
| 57.3% | 63% | 61% | 61% | 56% | 47% | 56% | |
| 45.7% | 46% | 49% | 49% | 44% | 40% | 46% | |
| 43.7% | 46% | 51% | 44% | 40% | 41% | 40% | |
| 61.3% | 59% | 57% | 62% | 62% | 68% | 60% |