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 | 11th 80.2% | 2nd 82.8% | 20th 78.0% | 19th 78.2% | 4th 82.5% | 16th 79.0% | 4th 82.5% | 13th 79.3% | 13th 79.3% | 13th 79.3% | 4th 82.5% | 2nd 82.8% | 9th 80.5% | 1st 83.8% | 21st 76.0% | 8th 81.8% | 18th 78.5% | 10th 80.3% | 4th 82.5% | 17th 78.8% | 12th 80.0% | |
| 83.7% | 82% | 83% | 80% | 76% | 84% | 80% | 81% | 86% | 86% | 79% | 87% | 88% | 89% | 97% | 64% | 88% | 81% | 87% | 88% | 88% | 84% | |
| 86.9% | 83% | 96% | 85% | 85% | 83% | 90% | 92% | 81% | 77% | 83% | 91% | 89% | 90% | 83% | 90% | 89% | 89% | 85% | 93% | 84% | 87% | |
| 66.7% | 70% | 70% | 70% | 70% | 69% | 68% | 70% | 57% | 63% | 69% | 69% | 69% | 60% | 62% | 68% | 68% | 65% | 59% | 71% | 67% | 67% | |
| 84.2% | 86% | 82% | 77% | 82% | 94% | 78% | 87% | 93% | 91% | 86% | 83% | 85% | 83% | 93% | 82% | 82% | 79% | 90% | 78% | 76% | 82% |