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 India. Source: Global Dialogues GD6 (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 82.4% | 4th 81.0% | 6th 73.4% | 2nd 81.6% | 3rd 81.1% | 5th 79.9% | |
| 82.7% | 88% | 90% | 68% | 79% | 89% | 82% | |
| 88.5% | 88% | 91% | 84% | 89% | 92% | 87% | |
| 77.8% | 67% | 67% | 83% | 83% | 79% | 88% | |
| 75.3% | 77% | 72% | 66% | 81% | 89% | 67% | |
| 71.7% | 91% | 60% | 53% | 78% | 66% | 82% | |
| 82.3% | 86% | 92% | 75% | 82% | 78% | 81% | |
| 78.8% | 86% | 87% | 67% | 81% | 76% | 76% | |
| 78.7% | 74% | 78% | 80% | 81% | 77% | 82% | |
| 82.5% | 94% | 83% | 68% | 85% | 86% | 79% | |
| 80.7% | 73% | 90% | 90% | 77% | 79% | 75% |