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 | 10th 75.0% | 6th 78.7% | 4th 79.7% | 1st 82.7% | 11th 74.7% | 3rd 79.7% | 2nd 82.0% | 9th 75.3% | 11th 74.7% | 5th 79.0% | 8th 75.3% | 7th 76.3% | 11th 74.7% | |
| 90.4% | 81% | 95% | 95% | 98% | 80% | 99% | 95% | 91% | 84% | 93% | 91% | 89% | 84% | |
| 63.8% | 65% | 65% | 68% | 67% | 66% | 61% | 67% | 61% | 63% | 63% | 54% | 64% | 65% | |
| 78.4% | 79% | 76% | 76% | 83% | 78% | 79% | 84% | 74% | 77% | 81% | 81% | 76% | 75% |