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 Malaysia. Source: Global Dialogues GD3 (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 72.0% | 1st 73.0% | 4th 68.2% | 5th 66.7% | 6th 63.7% | 3rd 71.6% | |
| 69.8% | 77% | 72% | 75% | 64% | 63% | 68% | |
| 77.0% | 86% | 92% | 66% | 63% | 79% | 76% | |
| 71.7% | 75% | 61% | 66% | 74% | 73% | 81% | |
| 70.2% | 73% | 70% | 62% | 73% | 71% | 72% | |
| 48.8% | 51% | 50% | 56% | 38% | 49% | ||
| 78.3% | 72% | 86% | 92% | 67% | 73% | 80% | |
| 85.5% | 83% | 89% | 80% | 88% | 85% | 88% | |
| 76.7% | 81% | 83% | 87% | 78% | 58% | 73% | |
| 58.5% | 66% | 49% | 68% | 48% | 52% | 68% | |
| 51.5% | 56% | 55% | 36% | 56% | 45% | 61% |