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 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 | 4th 69.4% | 3rd 72.7% | 5th 68.6% | 2nd 73.2% | 1st 74.2% | 6th 68.3% | |
| 85.5% | 81% | 85% | 86% | 86% | 92% | 83% | |
| 79.5% | 76% | 76% | 68% | 86% | 86% | 85% | |
| 61.8% | 55% | 65% | 63% | 61% | 58% | 69% | |
| 76.8% | 81% | 64% | 73% | 85% | 91% | 67% | |
| 66.7% | 68% | 63% | 62% | 63% | 75% | 69% | |
| 66.3% | 65% | 70% | 62% | 74% | 65% | 62% | |
| 63.2% | 61% | 69% | 66% | 65% | 60% | 58% | |
| 67.7% | 68% | 79% | 64% | 70% | 66% | 59% | |
| 70.7% | 71% | 74% | 66% | 71% | 72% | 70% | |
| 72.5% | 68% | 82% | 76% | 71% | 77% | 61% |