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 Equally concerned and excited. 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 | 5th 79.4% | 4th 79.6% | 1st 83.8% | 2nd 82.4% | 3rd 81.9% | 6th 76.2% | |
| 77.3% | 77% | 74% | 84% | 81% | 76% | 72% | |
| 81.3% | 80% | 88% | 75% | 82% | 86% | 77% | |
| 87.0% | 78% | 86% | 88% | 87% | 90% | 93% | |
| 79.0% | 77% | 73% | 93% | 75% | 81% | 75% | |
| 80.7% | 77% | 81% | 88% | 86% | 80% | 72% | |
| 81.0% | 79% | 84% | 82% | 83% | 77% | ||
| 76.5% | 77% | 78% | 75% | 77% | 83% | 69% | |
| 70.3% | 74% | 69% | 78% | 70% | 68% | 63% | |
| 86.3% | 88% | 84% | 91% | 89% | 84% | 82% | |
| 86.2% | 87% | 83% | 82% | 95% | 88% | 82% |