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 Germany. Source: Global Dialogues GD5 (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 80.6% | 2nd 80.7% | 1st 82.3% | 4th 78.3% | 6th 74.4% | 5th 77.3% | |
| 95.2% | 98% | 83% | 98% | 98% | 96% | 98% | |
| 81.0% | 82% | 82% | 83% | 84% | 83% | 72% | |
| 72.3% | 79% | 77% | 65% | 79% | 70% | 64% | |
| 92.5% | 92% | 92% | 95% | 92% | 97% | 87% | |
| 68.3% | 71% | 70% | 73% | 65% | 61% | 70% | |
| 79.3% | 79% | 80% | 80% | 79% | 79% | 79% | |
| 86.7% | 78% | 89% | 98% | 82% | 82% | 91% | |
| 83.8% | 86% | 85% | 83% | 89% | 77% | 83% | |
| 58.5% | 56% | 67% | 77% | 49% | 36% | 66% | |
| 71.7% | 85% | 82% | 71% | 66% | 63% | 63% |