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 Bangladesh. 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 65.3% | 2nd 66.0% | 6th 53.0% | 1st 67.3% | 5th 59.7% | 4th 62.7% | |
| 66.5% | 69% | 71% | 61% | 73% | 53% | 72% | |
| 57.3% | 65% | 67% | 43% | 67% | 51% | 51% | |
| 63.2% | 62% | 60% | 55% | 62% | 75% | 65% |