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 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 | 12th 70.0% | 2nd 78.0% | 9th 71.7% | 1st 79.3% | 8th 71.7% | 4th 75.7% | 6th 74.3% | 3rd 76.0% | 10th 71.3% | 13th 69.3% | 11th 71.0% | 5th 74.7% | 7th 73.7% | |
| 80.8% | 72% | 94% | 82% | 93% | 76% | 87% | 79% | 85% | 79% | 69% | 77% | 79% | 79% | |
| 58.8% | 56% | 65% | 57% | 62% | 61% | 55% | 57% | 57% | 55% | 59% | 56% | 62% | 62% | |
| 81.2% | 82% | 75% | 76% | 83% | 78% | 85% | 87% | 86% | 80% | 80% | 80% | 83% | 80% |