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 Spain. 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 | 3rd 62.0% | 2nd 65.2% | 5th 61.4% | 4th 61.7% | 6th 59.2% | 1st 67.1% | |
| 52.0% | 47% | 59% | 60% | 49% | 50% | 47% | |
| 57.7% | 56% | 43% | 59% | 59% | 59% | 70% | |
| 65.2% | 62% | 67% | 70% | 69% | 50% | 73% | |
| 51.8% | 49% | 38% | 49% | 55% | 65% | 55% | |
| 37.0% | 28% | 100% | 22% | 20% | 22% | 30% | |
| 61.5% | 65% | 67% | 62% | 63% | 56% | 56% | |
| 83.5% | 75% | 87% | 76% | 87% | 89% | 87% | |
| 84.5% | 100% | 74% | 85% | 78% | 78% | 92% | |
| 53.2% | 57% | 47% | 50% | 47% | 47% | 71% | |
| 81.3% | 81% | 70% | 81% | 90% | 76% | 90% |