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 3.7 Sonnet | Claude Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT 5 | GPT 5.1 | GPT OSS 120b | GPT OSS 20b | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 18th 72.3% | 11th 75.7% | 6th 78.7% | 4th 79.7% | 1st 82.0% | 11th 75.7% | 3rd 80.0% | 17th 73.0% | 5th 79.0% | 7th 78.3% | 15th 74.7% | 2nd 80.3% | 14th 75.0% | 13th 75.3% | 10th 76.0% | 16th 74.0% | 19th 71.7% | 8th 77.7% | 9th 76.3% | 20th 70.3% | |
| 89.5% | 75% | 81% | 95% | 95% | 97% | 80% | 99% | 89% | 95% | 94% | 84% | 93% | 91% | 91% | 89% | 84% | 87% | 87% | 89% | 94% | |
| 62.9% | 64% | 65% | 65% | 68% | 69% | 69% | 62% | 51% | 67% | 64% | 63% | 67% | 48% | 54% | 72% | 63% | 53% | 76% | 64% | 53% | |
| 76.6% | 78% | 81% | 76% | 76% | 80% | 78% | 79% | 79% | 75% | 77% | 77% | 81% | 86% | 81% | 67% | 75% | 75% | 70% | 76% | 64% |