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 Philippines. Source: Global Dialogues GD4 (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 | 2nd 60.1% | 5th 56.5% | 6th 55.8% | 3rd 59.7% | 4th 59.6% | 1st 62.8% | |
| 63.2% | 57% | 65% | 69% | 60% | 57% | 71% | |
| 46.8% | 49% | 45% | 40% | 47% | 50% | 50% | |
| 53.2% | 55% | 48% | 55% | 53% | 47% | 61% | |
| 58.3% | 55% | 39% | 55% | 58% | 69% | 74% | |
| 61.3% | 59% | 40% | 74% | 59% | 66% | 70% | |
| 62.3% | 67% | 67% | 56% | 67% | 59% | 58% | |
| 33.7% | 33% | 42% | 27% | 32% | 34% | 34% | |
| 56.7% | 64% | 63% | 43% | 59% | 58% | 53% | |
| 88.8% | 86% | 86% | 82% | 95% | 92% | 92% | |
| 66.5% | 76% | 70% | 57% | 67% | 64% | 65% |