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 Italy. Source: Global Dialogues GD7 (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 74.6% | 1st 76.4% | 2nd 74.7% | 5th 70.1% | 6th 66.8% | 4th 70.7% | |
| 75.2% | 83% | 82% | 79% | 63% | 69% | 75% | |
| 66.5% | 69% | 70% | 65% | 73% | 61% | 61% | |
| 61.5% | 64% | 71% | 66% | 61% | 55% | 52% | |
| 86.5% | 93% | 86% | 86% | 84% | 80% | 90% | |
| 78.2% | 76% | 79% | 86% | 80% | 68% | 80% | |
| 75.2% | 83% | 83% | 74% | 67% | 72% | 72% | |
| 70.7% | 69% | 80% | 81% | 66% | 59% | 69% | |
| 74.0% | 80% | 74% | 74% | 75% | 71% | 70% | |
| 71.3% | 75% | 79% | 68% | 68% | 68% | 70% | |
| 63.2% | 54% | 60% | 68% | 64% | 65% | 68% |