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 81.2% | 4th 82.5% | 21st 76.3% | 13th 79.2% | 2nd 83.0% | 17th 78.3% | 11th 80.0% | 14th 78.8% | 19th 76.8% | 15th 78.8% | 6th 82.0% | 3rd 82.5% | 7th 81.5% | 1st 83.8% | 12th 79.7% | 18th 77.5% | 10th 80.3% | 16th 78.5% | 8th 81.5% | 19th 76.8% | 4th 82.5% | |
| 83.1% | 84% | 83% | 73% | 80% | 84% | 77% | 81% | 87% | 77% | 78% | 85% | 87% | 91% | 97% | 77% | 70% | 86% | 88% | 88% | 80% | 93% | |
| 86.8% | 85% | 96% | 85% | 85% | 83% | 90% | 90% | 81% | 76% | 83% | 91% | 89% | 88% | 83% | 88% | 90% | 89% | 83% | 91% | 90% | 87% | |
| 66.2% | 70% | 69% | 70% | 70% | 69% | 68% | 62% | 56% | 63% | 69% | 69% | 69% | 62% | 62% | 70% | 64% | 63% | 67% | 69% | 61% | 68% | |
| 84.1% | 86% | 82% | 77% | 82% | 96% | 78% | 87% | 91% | 91% | 85% | 83% | 85% | 85% | 93% | 84% | 86% | 83% | 76% | 78% | 76% | 82% |