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 | 6th 77.8% | 3rd 82.8% | 1st 84.5% | 4th 82.1% | 2nd 84.1% | 5th 78.2% | |
| 81.5% | 80% | 84% | 87% | 79% | 83% | 76% | |
| 82.2% | 75% | 93% | 74% | 87% | 87% | 77% | |
| 88.3% | 78% | 88% | 90% | 87% | 98% | 89% | |
| 79.8% | 69% | 73% | 89% | 82% | 89% | 77% | |
| 82.7% | 81% | 79% | 83% | 86% | 81% | 86% | |
| 82.3% | 80% | 95% | 79% | 80% | 85% | 75% | |
| 80.3% | 84% | 76% | 87% | 84% | 79% | 72% | |
| 71.2% | 68% | 78% | 76% | 70% | 69% | 66% | |
| 84.3% | 87% | 84% | 94% | 79% | 84% | 78% | |
| 83.2% | 76% | 78% | 86% | 87% | 86% | 86% |