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 More excited than concerned. 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 | 2nd 84.8% | 1st 85.3% | 4th 81.0% | 3rd 84.3% | 5th 80.1% | 6th 78.4% | |
| 85.2% | 87% | 92% | 81% | 91% | 84% | 76% | |
| 80.3% | 84% | 78% | 74% | 85% | 86% | 75% | |
| 83.3% | 82% | 91% | 69% | 88% | 89% | 81% | |
| 77.5% | 80% | 87% | 73% | 79% | 71% | 75% | |
| 86.7% | 89% | 88% | 88% | 90% | 75% | 90% | |
| 86.2% | 89% | 85% | 81% | 89% | 87% | 86% | |
| 79.0% | 79% | 84% | 86% | 88% | 68% | 69% | |
| 72.8% | 83% | 70% | 81% | 71% | 74% | 58% | |
| 86.7% | 94% | 95% | 88% | 76% | 84% | 83% | |
| 85.5% | 81% | 83% | 89% | 86% | 83% | 91% |