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 Kenya. 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 | 5th 70.8% | 3rd 71.2% | 6th 67.8% | 1st 75.7% | 2nd 71.4% | 4th 71.0% | |
| 71.0% | 73% | 72% | 67% | 69% | 73% | 72% | |
| 66.2% | 65% | 69% | 55% | 64% | 73% | 71% | |
| 74.8% | 71% | 77% | 67% | 76% | 81% | 77% | |
| 56.2% | 68% | 67% | 36% | 76% | 50% | 40% | |
| 83.2% | 90% | 82% | 84% | 82% | 77% | 84% | |
| 64.0% | 60% | 71% | 67% | 65% | 62% | 59% | |
| 75.2% | 76% | 59% | 69% | 92% | 71% | 84% | |
| 76.8% | 70% | 80% | 83% | 80% | 75% | 73% | |
| 66.8% | 67% | 56% | 71% | 70% | 67% | 70% | |
| 79.0% | 68% | 79% | 79% | 83% | 85% | 80% |