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 GD3 (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 | 1st 70.8% | 2nd 68.5% | 5th 64.0% | 3rd 65.8% | 4th 64.8% | 6th 63.9% | |
| 71.0% | 72% | 76% | 69% | 69% | 77% | 63% | |
| 73.7% | 87% | 93% | 68% | 70% | 59% | 65% | |
| 64.5% | 65% | 64% | 55% | 66% | 75% | 62% | |
| 78.3% | 100% | 80% | 83% | 78% | 62% | 67% | |
| 45.8% | 47% | 72% | 40% | 45% | 27% | 44% | |
| 66.8% | 58% | 72% | 69% | 59% | 74% | 69% | |
| 64.7% | 67% | 61% | 69% | 63% | 66% | 62% | |
| 78.5% | 80% | 86% | 72% | 86% | 76% | 71% | |
| 62.5% | 71% | 26% | 69% | 64% | 70% | 75% | |
| 57.2% | 61% | 55% | 46% | 58% | 62% | 61% |