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 Rural. Source: Global Dialogues GD1 (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 | 1st 88.8% | 4th 84.0% | 5th 82.5% | 2nd 88.3% | 6th 80.0% | 3rd 85.5% | |
| 82.3% | 81% | 78% | 70% | 87% | 86% | 92% | |
| 86.0% | 94% | 76% | 84% | 90% | 86% | 86% | |
| 79.3% | 86% | 87% | 86% | 78% | 62% | 77% | |
| 91.7% | 94% | 95% | 90% | 98% | 86% | 87% |