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 Mexico. Source: Global Dialogues GD6 (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 68.4% | 2nd 69.1% | 4th 66.6% | 1st 69.6% | 6th 61.6% | 5th 66.1% | |
| 58.7% | 56% | 67% | 57% | 63% | 52% | 57% | |
| 69.2% | 75% | 77% | 71% | 75% | 64% | 53% | |
| 65.3% | 71% | 71% | 60% | 70% | 47% | 73% | |
| 53.8% | 60% | 49% | 49% | 60% | 46% | 59% | |
| 56.8% | 65% | 63% | 51% | 48% | 64% | 50% | |
| 75.5% | 66% | 78% | 76% | 79% | 70% | 84% | |
| 75.5% | 80% | 81% | 75% | 70% | 68% | 79% | |
| 78.2% | 78% | 70% | 82% | 82% | 81% | 76% | |
| 64.5% | 60% | 60% | 75% | 68% | 62% | 62% | |
| 71.5% | 73% | 75% | 70% | 81% | 62% | 68% |