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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 14th 80.3% | 3rd 84.2% | 8th 82.7% | 4th 83.3% | 1st 85.5% | 16th 79.0% | 7th 82.8% | 18th 77.3% | 11th 81.0% | 17th 78.8% | 5th 83.0% | 2nd 84.3% | 5th 83.0% | 9th 82.3% | 21st 75.8% | 13th 80.5% | 12th 80.7% | 20th 76.0% | 10th 81.8% | 19th 77.0% | 15th 79.3% | |
| 80.1% | 83% | 86% | 77% | 76% | 84% | 78% | 85% | 78% | 86% | 74% | 83% | 87% | 85% | 88% | 63% | 71% | 84% | 83% | 82% | 77% | 73% | |
| 84.4% | 84% | 85% | 86% | 86% | 88% | 81% | 89% | 79% | 79% | 86% | 92% | 89% | 89% | 83% | 82% | 83% | 79% | 84% | 85% | 79% | 85% | |
| 67.4% | 71% | 72% | 72% | 75% | 72% | 67% | 68% | 57% | 63% | 63% | 69% | 69% | 68% | 60% | 66% | 76% | 72% | 52% | 70% | 64% | 70% | |
| 91.5% | 83% | 94% | 96% | 96% | 98% | 90% | 89% | 95% | 96% | 92% | 88% | 92% | 90% | 98% | 92% | 92% | 88% | 85% | 90% | 88% | 89% |