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 | 3rd 86.5% | 2nd 87.1% | 4th 84.6% | 1st 87.3% | 6th 82.2% | 5th 82.3% | |
| 87.7% | 89% | 93% | 90% | 92% | 81% | 81% | |
| 79.0% | 82% | 76% | 86% | 78% | 76% | 76% | |
| 84.2% | 83% | 95% | 73% | 88% | 89% | 77% | |
| 90.2% | 96% | 94% | 85% | 92% | 87% | 87% | |
| 90.7% | 88% | 93% | 92% | 91% | 85% | 95% | |
| 86.3% | 91% | 91% | 82% | 87% | 89% | 78% | |
| 86.5% | 88% | 87% | 88% | 91% | 77% | 88% | |
| 70.3% | 78% | 72% | 73% | 77% | 63% | 59% | |
| 88.0% | 82% | 87% | 90% | 84% | 89% | 96% | |
| 87.2% | 88% | 83% | 87% | 93% | 86% | 86% |