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 GD4 (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 66.1% | 6th 57.6% | 4th 64.2% | 3rd 65.7% | 5th 63.4% | 1st 68.3% | |
| 65.2% | 64% | 62% | 66% | 68% | 61% | 70% | |
| 56.0% | 60% | 54% | 51% | 54% | 63% | 54% | |
| 68.3% | 72% | 60% | 69% | 73% | 65% | 71% | |
| 50.3% | 53% | 52% | 40% | 45% | 54% | 58% | |
| 72.0% | 85% | 10% | 81% | 84% | 89% | 83% | |
| 70.7% | 76% | 73% | 84% | 71% | 49% | 71% | |
| 50.7% | 43% | 51% | 44% | 48% | 58% | 60% | |
| 56.8% | 57% | 60% | 57% | 55% | 55% | 57% | |
| 88.2% | 90% | 99% | 66% | 94% | 90% | 90% | |
| 64.0% | 61% | 55% | 84% | 65% | 50% | 69% |