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 GD1 (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 77.5% | 5th 69.3% | 1st 94.0% | 3rd 76.5% | 6th 61.5% | 4th 74.0% | |
| 59.6% | 54% | 73% | 58% | 59% | 54% | ||
| 82.2% | 83% | 79% | 88% | 68% | 93% | ||
| 58.6% | 76% | 58% | 64% | 37% | 58% | ||
| 87.8% | 97% | 67% | 94% | 96% | 82% | 91% |