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 | 3rd 63.0% | 6th 60.6% | 4th 61.6% | 2nd 66.6% | 5th 61.3% | 1st 66.9% | |
| 65.5% | 63% | 59% | 66% | 71% | 63% | 71% | |
| 75.2% | 80% | 75% | 60% | 77% | 78% | 81% | |
| 67.8% | 65% | 62% | 73% | 73% | 73% | 61% | |
| 59.2% | 65% | 38% | 52% | 55% | 65% | 80% | |
| 74.2% | 76% | 80% | 78% | 79% | 66% | 66% | |
| 57.5% | 53% | 53% | 63% | 65% | 46% | 65% | |
| 39.2% | 36% | 47% | 35% | 36% | 36% | 45% | |
| 71.0% | 68% | 71% | 71% | 77% | 67% | 72% | |
| 54.7% | 58% | 57% | 52% | 58% | 52% | 51% | |
| 69.2% | 66% | 64% | 66% | 75% | 67% | 77% |