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 | 8th 69.7% | 8th 69.7% | 8th 69.7% | 1st 76.7% | 13th 65.7% | 8th 69.7% | 3rd 72.3% | 12th 67.7% | 6th 71.0% | 2nd 72.7% | 6th 71.0% | 5th 71.7% | 4th 72.0% | |
| 67.2% | 58% | 70% | 70% | 80% | 55% | 76% | 70% | 70% | 64% | 64% | 64% | 68% | 64% | |
| 69.5% | 74% | 72% | 72% | 75% | 75% | 56% | 65% | 61% | 66% | 72% | 69% | 75% | 72% | |
| 75.5% | 77% | 67% | 67% | 75% | 67% | 77% | 82% | 72% | 83% | 82% | 80% | 72% | 80% |