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 | 3rd 74.7% | 5th 71.9% | 6th 68.3% | 1st 77.1% | 4th 74.2% | 2nd 75.5% | |
| 89.5% | 93% | 89% | 79% | 93% | 93% | 90% | |
| 64.0% | 66% | 64% | 60% | 59% | 72% | 63% | |
| 84.7% | 89% | 89% | 81% | 100% | 69% | 80% | |
| 78.7% | 76% | 84% | 77% | 79% | 78% | 78% | |
| 60.2% | 67% | 56% | 44% | 61% | 72% | 61% | |
| 67.2% | 61% | 55% | 77% | 70% | 71% | 69% | |
| 70.0% | 75% | 77% | 60% | 68% | 69% | 71% | |
| 75.0% | 65% | 65% | 78% | 91% | 65% | 86% | |
| 71.8% | 81% | 74% | 59% | 70% | 73% | 74% | |
| 75.2% | 74% | 66% | 68% | 80% | 80% | 83% |