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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 16th 73.3% | 13th 75.0% | 7th 78.3% | 4th 79.7% | 1st 81.3% | 9th 76.3% | 3rd 79.7% | 14th 74.0% | 6th 78.3% | 2nd 80.0% | 20th 72.0% | 5th 78.7% | 15th 73.7% | 12th 75.3% | 19th 72.3% | 18th 72.7% | 9th 76.3% | 21st 64.0% | 9th 76.3% | 16th 73.3% | 8th 77.0% | |
| 89.1% | 75% | 81% | 95% | 95% | 95% | 80% | 99% | 95% | 87% | 96% | 84% | 93% | 90% | 91% | 88% | 81% | 87% | 83% | 89% | 93% | 94% | |
| 60.4% | 64% | 65% | 64% | 68% | 69% | 69% | 61% | 50% | 64% | 64% | 55% | 62% | 48% | 54% | 62% | 68% | 65% | 33% | 64% | 53% | 67% | |
| 77.3% | 81% | 79% | 76% | 76% | 80% | 80% | 79% | 77% | 84% | 80% | 77% | 81% | 83% | 81% | 67% | 69% | 77% | 76% | 76% | 74% | 70% |