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 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 | Grok 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 15th 78.5% | 3rd 84.2% | 6th 82.5% | 5th 83.3% | 1st 84.5% | 11th 80.0% | 7th 82.3% | 18th 77.5% | 8th 81.5% | 12th 79.8% | 9th 81.0% | 1st 84.5% | 13th 79.3% | 4th 84.0% | 17th 77.8% | 16th 78.3% | 20th 75.5% | 14th 79.0% | 10th 80.8% | 21st 75.0% | 19th 76.0% | |
| 78.8% | 81% | 86% | 76% | 76% | 84% | 78% | 84% | 80% | 86% | 73% | 83% | 87% | 88% | 87% | 63% | 66% | 76% | 86% | 78% | 74% | 63% | |
| 84.6% | 84% | 85% | 86% | 86% | 88% | 85% | 89% | 76% | 79% | 86% | 92% | 90% | 84% | 91% | 83% | 84% | 83% | 84% | 85% | 75% | 81% | |
| 66.2% | 71% | 72% | 72% | 75% | 68% | 67% | 67% | 57% | 63% | 68% | 61% | 69% | 55% | 60% | 70% | 76% | 55% | 57% | 70% | 63% | 74% | |
| 91.4% | 78% | 94% | 96% | 96% | 98% | 90% | 89% | 97% | 98% | 92% | 88% | 92% | 90% | 98% | 95% | 87% | 88% | 89% | 90% | 88% | 86% |