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 concerned than 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 78.3% | 2nd 78.4% | 1st 81.1% | 5th 74.3% | 6th 72.2% | 4th 78.2% | |
| 83.8% | 83% | 85% | 84% | 86% | 79% | 86% | |
| 58.5% | 63% | 84% | 67% | 57% | 13% | 67% | |
| 76.8% | 72% | 76% | 81% | 78% | 76% | 78% | |
| 85.3% | 86% | 87% | 86% | 81% | 85% | 87% | |
| 68.5% | 72% | 59% | 69% | 79% | 62% | 70% | |
| 88.5% | 90% | 84% | 95% | 87% | 86% | 89% | |
| 64.2% | 74% | 80% | 78% | 26% | 61% | 66% | |
| 86.5% | 84% | 81% | 90% | 89% | 85% | 90% | |
| 77.5% | 82% | 71% | 77% | 79% | 88% | 68% | |
| 81.2% | 77% | 77% | 84% | 81% | 87% | 81% |