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 [synth]: 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 57.3% | 3rd 57.8% | 2nd 60.2% | 5th 54.8% | 6th 52.6% | 1st 60.7% | |
| 56.5% | 62% | 53% | 66% | 53% | 53% | 52% | |
| 81.2% | 61% | 100% | 45% | 100% | 100% | ||
| 56.3% | 60% | 60% | 63% | 54% | 44% | 57% | |
| 54.0% | 63% | 44% | 59% | 52% | 52% | ||
| 45.6% | 45% | 31% | 47% | 88% | 17% | ||
| 68.4% | 67% | 67% | 74% | 67% | 67% | ||
| 49.8% | 27% | 67% | 60% | 18% | 65% | 62% | |
| 62.8% | 64% | 59% | 70% | 69% | 57% | 58% | |
| 40.7% | 66% | 39% | 39% | 43% | 18% | 39% | |
| 58.2% | 58% | 58% | 64% | 59% | 53% | 57% |