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 | 17th 72.7% | 11th 75.0% | 7th 78.3% | 4th 79.7% | 1st 82.3% | 11th 75.0% | 3rd 80.0% | 15th 74.3% | 5th 78.7% | 5th 78.7% | 14th 74.7% | 2nd 80.3% | 11th 75.0% | 8th 77.0% | 19th 70.7% | 9th 76.0% | 21st 68.3% | 20th 69.0% | 10th 75.3% | 18th 72.3% | 15th 74.3% | |
| 88.9% | 75% | 81% | 95% | 95% | 98% | 80% | 99% | 95% | 95% | 96% | 84% | 93% | 90% | 95% | 82% | 81% | 84% | 83% | 89% | 87% | 90% | |
| 61.6% | 64% | 65% | 64% | 68% | 69% | 67% | 62% | 50% | 67% | 64% | 63% | 67% | 52% | 55% | 63% | 73% | 44% | 52% | 64% | 56% | 64% | |
| 76.3% | 79% | 79% | 76% | 76% | 80% | 78% | 79% | 78% | 74% | 76% | 77% | 81% | 83% | 81% | 67% | 74% | 77% | 72% | 73% | 74% | 69% |