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 Vietnam. 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 | 4th 61.4% | 6th 60.6% | 5th 61.1% | 2nd 63.4% | 3rd 62.9% | 1st 64.4% | |
| 67.0% | 59% | 61% | 66% | 71% | 74% | 71% | |
| 75.2% | 80% | 72% | 60% | 77% | 79% | 83% | |
| 64.3% | 63% | 59% | 73% | 57% | 73% | 61% | |
| 58.2% | 67% | 40% | 46% | 51% | 65% | 80% | |
| 73.0% | 76% | 73% | 78% | 79% | 66% | 66% | |
| 56.7% | 53% | 56% | 63% | 60% | 48% | 60% | |
| 38.2% | 35% | 52% | 35% | 36% | 36% | 35% | |
| 70.8% | 68% | 72% | 72% | 77% | 67% | 69% | |
| 53.3% | 47% | 57% | 52% | 55% | 56% | 53% | |
| 66.3% | 66% | 64% | 66% | 71% | 65% | 66% |