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 | 8th 81.0% | 9th 80.5% | 15th 79.0% | 18th 78.2% | 5th 82.3% | 19th 78.0% | 10th 80.3% | 12th 79.8% | 17th 78.3% | 15th 79.0% | 6th 82.0% | 4th 82.5% | 2nd 83.0% | 1st 83.5% | 21st 76.5% | 14th 79.3% | 10th 80.3% | 20th 76.8% | 3rd 82.8% | 12th 79.8% | 7th 81.2% | |
| 83.4% | 81% | 83% | 80% | 76% | 81% | 77% | 81% | 87% | 86% | 77% | 85% | 89% | 92% | 96% | 70% | 78% | 91% | 84% | 83% | 87% | 87% | |
| 87.0% | 87% | 93% | 85% | 85% | 83% | 89% | 90% | 83% | 76% | 82% | 91% | 92% | 88% | 83% | 89% | 87% | 89% | 90% | 92% | 87% | 87% | |
| 66.8% | 70% | 69% | 69% | 70% | 69% | 68% | 62% | 57% | 60% | 69% | 69% | 69% | 69% | 62% | 65% | 69% | 66% | 60% | 69% | 72% | 69% | |
| 83.5% | 86% | 77% | 82% | 82% | 96% | 78% | 88% | 92% | 91% | 88% | 83% | 80% | 83% | 93% | 82% | 83% | 75% | 73% | 87% | 73% | 82% |