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 GD4 (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 83.5% | 2nd 85.5% | 1st 94.0% | 4th 81.1% | 6th 75.4% | 5th 80.1% | |
| 86.8% | 86% | 92% | 90% | 84% | 82% | ||
| 43.4% | 50% | 44% | 41% | 41% | 41% | ||
| 87.4% | 89% | 89% | 90% | 83% | 86% | ||
| 81.4% | 92% | 81% | 94% | 69% | 71% | ||
| 77.6% | 75% | 90% | 81% | 60% | 82% | ||
| 89.6% | 97% | 91% | 79% | 87% | 94% | ||
| 88.6% | 95% | 95% | 84% | 84% | 85% | ||
| 83.4% | 81% | 91% | 79% | 79% | 87% | ||
| 86.6% | 83% | 91% | 86% | 90% | 83% | ||
| 87.7% | 87% | 91% | 94% | 87% | 77% | 90% |