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 Japan. 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 | 3rd 70.5% | 4th 66.8% | 5th 65.8% | 2nd 71.2% | 6th 60.8% | 1st 72.8% | |
| 67.5% | 69% | 69% | 68% | 67% | 62% | 70% | |
| 65.7% | 69% | 63% | 63% | 71% | 57% | 71% | |
| 51.0% | 58% | 63% | 46% | 53% | 33% | 53% | |
| 87.7% | 86% | 72% | 86% | 94% | 91% | 97% |