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 United States. 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 | 6th 82.0% | 10th 79.2% | 11th 78.2% | 8th 80.8% | 12th 77.8% | 4th 82.5% | 13th 77.0% | 3rd 83.2% | 1st 84.3% | 7th 81.5% | 2nd 83.5% | 9th 80.5% | 5th 82.0% | |
| 83.6% | 83% | 80% | 76% | 84% | 77% | 81% | 77% | 84% | 92% | 88% | 97% | 83% | 85% | |
| 87.9% | 93% | 85% | 85% | 83% | 89% | 90% | 76% | 91% | 93% | 89% | 83% | 92% | 94% | |
| 68.6% | 70% | 70% | 70% | 69% | 67% | 71% | 64% | 72% | 69% | 69% | 61% | 69% | 71% | |
| 83.7% | 82% | 82% | 82% | 87% | 78% | 88% | 91% | 86% | 83% | 80% | 93% | 78% | 78% |