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 Brazil. 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 78.1% | 1st 78.8% | 5th 72.1% | 3rd 77.1% | 6th 71.7% | 4th 75.5% | |
| 75.7% | 80% | 72% | 68% | 78% | 78% | 78% | |
| 82.0% | 86% | 90% | 71% | 80% | 74% | 91% | |
| 69.2% | 68% | 71% | 64% | 71% | 68% | 73% | |
| 77.5% | 89% | 90% | 59% | 93% | 59% | 75% | |
| 75.8% | 74% | 67% | 76% | 78% | 81% | 79% | |
| 64.3% | 61% | 73% | 64% | 63% | 67% | 58% | |
| 85.8% | 80% | 91% | 85% | 87% | 86% | 86% | |
| 69.8% | 71% | 75% | 83% | 69% | 49% | 72% | |
| 74.0% | 75% | 73% | 72% | 73% | 75% | 76% | |
| 81.3% | 97% | 86% | 79% | 79% | 80% | 67% |