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 | 9th 81.5% | 3rd 82.8% | 17th 79.2% | 8th 81.7% | 19th 78.3% | 20th 75.0% | 14th 80.3% | 13th 80.3% | 18th 78.3% | 11th 80.5% | 1st 84.8% | 7th 82.0% | 9th 81.5% | 2nd 83.0% | 5th 82.3% | 11th 80.5% | 15th 79.8% | 16th 79.5% | 6th 82.0% | 3rd 82.8% | 21st 74.5% | |
| 84.6% | 84% | 83% | 80% | 76% | 81% | 77% | 81% | 87% | 86% | 80% | 92% | 85% | 88% | 94% | 86% | 86% | 82% | 86% | 88% | 87% | 87% | |
| 86.8% | 88% | 96% | 85% | 85% | 79% | 86% | 90% | 81% | 76% | 83% | 93% | 89% | 88% | 83% | 87% | 85% | 90% | 90% | 88% | 88% | 92% | |
| 66.4% | 70% | 70% | 70% | 70% | 70% | 59% | 62% | 60% | 60% | 71% | 69% | 69% | 68% | 62% | 68% | 67% | 60% | 66% | 69% | 66% | 68% | |
| 84.2% | 84% | 82% | 82% | 96% | 83% | 78% | 88% | 93% | 91% | 88% | 85% | 85% | 82% | 93% | 88% | 84% | 87% | 76% | 83% | 90% | 51% |