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 | Grok 4 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 76.0% | 16th 70.0% | 1st 78.3% | 11th 71.7% | 2nd 78.3% | 19th 69.0% | 3rd 76.0% | 5th 75.3% | 10th 72.0% | 6th 75.0% | 17th 69.7% | 9th 73.3% | 15th 70.3% | 11th 71.7% | 17th 69.7% | 14th 70.3% | 8th 73.3% | 20th 69.0% | 7th 74.7% | 21st 63.3% | 13th 71.3% | |
| 79.8% | 87% | 72% | 94% | 82% | 95% | 76% | 87% | 95% | 79% | 85% | 79% | 73% | 79% | 77% | 80% | 72% | 81% | 73% | 79% | 65% | 65% | |
| 56.8% | 62% | 56% | 66% | 57% | 62% | 53% | 54% | 48% | 54% | 54% | 54% | 59% | 47% | 56% | 60% | 63% | 59% | 59% | 62% | 45% | 63% | |
| 80.3% | 79% | 82% | 75% | 76% | 78% | 78% | 87% | 83% | 83% | 86% | 76% | 88% | 85% | 82% | 69% | 76% | 80% | 75% | 83% | 80% | 86% |