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 South Africa. 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 | 2nd 67.3% | 1st 68.8% | 6th 58.5% | 4th 64.3% | 5th 62.3% | 3rd 65.5% | |
| 63.0% | 64% | 62% | 56% | 62% | 67% | 67% | |
| 71.5% | 68% | 77% | 69% | 72% | 67% | 76% | |
| 53.7% | 59% | 69% | 47% | 50% | 47% | 50% | |
| 69.5% | 78% | 67% | 62% | 73% | 68% | 69% |