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 GD2 (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 | 11th 62.0% | 9th 64.3% | 5th 67.7% | 4th 68.0% | 13th 58.0% | 7th 67.0% | 11th 62.0% | 10th 64.0% | 5th 67.7% | 8th 65.0% | 1st 76.5% | 2nd 69.3% | 2nd 69.3% | |
| 63.9% | 51% | 60% | 70% | 75% | 54% | 68% | 65% | 73% | 60% | 62% | 64% | 65% | ||
| 57.2% | 58% | 61% | 56% | 67% | 51% | 56% | 45% | 47% | 63% | 54% | 59% | 68% | 59% | |
| 76.5% | 77% | 72% | 77% | 62% | 69% | 77% | 76% | 72% | 80% | 79% | 94% | 76% | 84% |