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 Kingdom. 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 | 18th 75.0% | 5th 79.7% | 9th 77.7% | 4th 80.0% | 1st 83.7% | 19th 74.7% | 11th 77.3% | 16th 76.0% | 7th 79.0% | 14th 77.0% | 15th 76.7% | 3rd 80.3% | 12th 77.0% | 2nd 81.3% | 8th 78.3% | 6th 79.3% | 19th 74.7% | 17th 75.3% | 12th 77.0% | 21st 74.0% | 9th 77.7% | |
| 82.9% | 76% | 77% | 86% | 84% | 87% | 72% | 85% | 84% | 83% | 86% | 81% | 84% | 84% | 87% | 86% | 82% | 80% | 84% | 81% | 84% | 88% | |
| 69.5% | 71% | 73% | 73% | 82% | 79% | 72% | 71% | 59% | 66% | 69% | 63% | 71% | 56% | 63% | 77% | 77% | 71% | 60% | 71% | 62% | 73% | |
| 80.7% | 78% | 89% | 74% | 74% | 85% | 80% | 76% | 85% | 88% | 76% | 86% | 86% | 91% | 94% | 72% | 79% | 73% | 82% | 79% | 76% | 72% |