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 GD1 (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 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | Qwen3 30b A3B Instruct 2507 | Qwen3 Next 80b A3B Instruct | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 82.8% | 7th 77.3% | 8th 76.0% | 13th 72.5% | 11th 73.5% | 10th 73.8% | 9th 75.0% | 6th 79.3% | 1st 85.5% | 12th 72.8% | 4th 82.5% | 5th 80.0% | 2nd 83.8% | |
| 77.3% | 79% | 71% | 71% | 78% | 61% | 78% | 79% | 78% | 89% | 75% | 89% | 77% | 80% | |
| 71.5% | 78% | 63% | 72% | 64% | 70% | 74% | 64% | 69% | 78% | 71% | 72% | 75% | 80% | |
| 85.2% | 91% | 91% | 84% | 83% | 86% | 72% | 82% | 93% | 91% | 67% | 86% | 90% | 91% | |
| 78.2% | 83% | 84% | 77% | 65% | 77% | 71% | 75% | 77% | 84% | 78% | 83% | 78% | 84% |