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 | 4th 75.9% | 2nd 76.9% | 1st 80.3% | 6th 71.7% | 5th 75.7% | 3rd 76.8% | |
| 84.5% | 81% | 79% | 88% | 83% | 95% | 81% | |
| 63.2% | 58% | 77% | 67% | 59% | 55% | 63% | |
| 78.5% | 76% | 77% | 84% | 83% | 66% | 85% | |
| 77.0% | 79% | 75% | 86% | 55% | 82% | 85% | |
| 70.3% | 82% | 72% | 65% | 75% | 62% | 66% | |
| 85.2% | 86% | 84% | 86% | 90% | 78% | 87% | |
| 62.2% | 64% | 84% | 77% | 22% | 64% | 62% | |
| 84.8% | 73% | 79% | 89% | 89% | 90% | 89% | |
| 74.3% | 78% | 66% | 77% | 79% | 78% | 68% | |
| 82.2% | 82% | 76% | 84% | 82% | 87% | 82% |