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 GD5 (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 68.8% | 3rd 67.9% | 5th 63.5% | 1st 69.4% | 6th 62.1% | 4th 65.6% | |
| 55.5% | 58% | 54% | 47% | 58% | 59% | 57% | |
| 65.2% | 68% | 75% | 53% | 65% | 66% | 64% | |
| 55.2% | 54% | 61% | 50% | 55% | 59% | 52% | |
| 55.3% | 73% | 74% | 31% | 68% | 30% | 56% | |
| 70.3% | 71% | 65% | 67% | 74% | 71% | 74% | |
| 72.8% | 69% | 69% | 77% | 75% | 70% | 77% | |
| 71.7% | 73% | 73% | 69% | 77% | 67% | 71% | |
| 74.2% | 78% | 71% | 81% | 81% | 59% | 75% | |
| 79.7% | 73% | 72% | 93% | 81% | 78% | 81% | |
| 62.3% | 71% | 65% | 67% | 60% | 62% | 49% |