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.
Evaluates a model's ability to provide concise (50-80 words), culturally appropriate, and actionable maternal health information for women in rural/semi-urban India.
Average key point coverage extent for each model across all prompts.
| Prompts vs. Models | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | |
|---|---|---|---|---|---|---|
| Score | 2nd 26.8% | 3rd 24.1% | 1st 27.5% | 5th 22.2% | 4th 22.3% | |
| 27.0% | 19% | 29% | 35% | 27% | 25% | |
| 16.0% | 18% | 14% | 14% | 16% | 18% | |
| 17.6% | 19% | 20% | 18% | 15% | 16% | |
| 22.0% | 19% | 19% | 26% | 23% | 23% | |
| 14.8% | 15% | 14% | 17% | 13% | 15% | |
| 33.4% | 44% | 31% | 37% | 24% | 31% | |
| 36.2% | 42% | 38% | 36% | 36% | 29% | |
| 30.6% | 34% | 26% | 36% | 28% | 29% | |
| 31.2% | 45% | 32% | 39% | 21% | 19% | |
| 17.0% | 13% | 18% | 17% | 19% | 18% |