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 I do not identify with any religious group or faith. Source: Global Dialogues GD2 (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 76.7% | 2nd 81.0% | 6th 67.3% | 4th 74.0% | 5th 71.3% | 1st 81.7% | |
| 77.3% | 71% | 93% | 71% | 71% | 73% | 85% | |
| 67.0% | 76% | 69% | 65% | 66% | 60% | 66% | |
| 81.7% | 83% | 81% | 66% | 85% | 81% | 94% |