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 | 2nd 76.8% | 6th 73.3% | 11th 71.5% | 12th 71.2% | 7th 72.5% | 8th 72.3% | 10th 71.8% | 13th 65.5% | 4th 74.0% | 5th 73.5% | 3rd 74.3% | 8th 72.3% | 1st 80.5% | |
| 74.5% | 75% | 71% | 67% | 75% | 65% | 79% | 79% | 63% | 80% | 81% | 83% | 71% | 80% | |
| 65.5% | 68% | 61% | 63% | 58% | 67% | 69% | 61% | 56% | 68% | 68% | 68% | 68% | 76% | |
| 79.8% | 87% | 88% | 88% | 82% | 83% | 77% | 75% | 75% | 70% | 77% | 71% | 82% | 82% | |
| 72.3% | 77% | 73% | 68% | 70% | 75% | 64% | 72% | 68% | 78% | 68% | 75% | 68% | 84% |