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 GD6 (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 78.0% | 5th 74.2% | 6th 70.4% | 4th 74.4% | 2nd 76.1% | 3rd 76.0% | |
| 92.0% | 97% | 92% | 89% | 90% | 90% | 94% | |
| 71.7% | 71% | 70% | 69% | 74% | 74% | 72% | |
| 84.8% | 92% | 83% | 72% | 90% | 83% | 89% | |
| 72.3% | 78% | 72% | 69% | 70% | 78% | 67% | |
| 64.3% | 71% | 57% | 57% | 59% | 72% | 70% | |
| 65.0% | 55% | 64% | 76% | 69% | 57% | 69% | |
| 72.0% | 80% | 77% | 64% | 70% | 71% | 70% | |
| 77.5% | 79% | 75% | 75% | 76% | 84% | 76% | |
| 72.3% | 79% | 80% | 59% | 75% | 67% | 74% | |
| 76.5% | 78% | 72% | 74% | 71% | 85% | 79% |