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 | 4th 81.3% | 8th 77.3% | 10th 76.3% | 11th 75.5% | 12th 74.3% | 9th 77.0% | 7th 78.3% | 6th 79.8% | 3rd 81.5% | 13th 73.5% | 5th 81.0% | 2nd 81.8% | 1st 83.8% | |
| 78.2% | 79% | 71% | 75% | 78% | 61% | 78% | 74% | 83% | 88% | 75% | 89% | 86% | 80% | |
| 70.4% | 78% | 63% | 69% | 70% | 70% | 75% | 64% | 66% | 78% | 58% | 72% | 72% | 80% | |
| 87.8% | 91% | 91% | 84% | 83% | 86% | 84% | 97% | 93% | 82% | 83% | 86% | 91% | 91% | |
| 77.7% | 77% | 84% | 77% | 71% | 80% | 71% | 78% | 77% | 78% | 78% | 77% | 78% | 84% |