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 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 | 3rd 71.3% | 1st 76.0% | 5th 70.4% | 4th 71.2% | 6th 62.6% | 2nd 72.4% | |
| 70.5% | 70% | 75% | 79% | 73% | 54% | 72% | |
| 84.2% | 93% | 95% | 67% | 92% | 68% | 90% | |
| 71.5% | 75% | 74% | 79% | 77% | 63% | 61% | |
| 58.3% | 64% | 61% | 65% | 64% | 29% | 67% | |
| 65.8% | 66% | 87% | 65% | 54% | 53% | 70% | |
| 81.5% | 76% | 84% | 79% | 76% | 86% | 88% | |
| 58.7% | 58% | 55% | 60% | 58% | 57% | 64% | |
| 78.3% | 85% | 83% | 78% | 73% | 80% | 71% | |
| 71.7% | 67% | 81% | 71% | 83% | 57% | 71% | |
| 66.0% | 59% | 65% | 61% | 62% | 79% | 70% |