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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 84.3% | 11th 77.0% | 17th 74.0% | 7th 79.0% | 1st 84.7% | 19th 70.7% | 12th 76.7% | 4th 81.7% | 15th 75.7% | 10th 77.7% | 3rd 82.7% | 12th 76.7% | 18th 73.3% | 6th 80.7% | 9th 78.3% | 12th 76.7% | 7th 79.0% | 21st 67.0% | 4th 81.7% | 16th 75.0% | 20th 67.0% | |
| 82.5% | 94% | 82% | 73% | 89% | 96% | 72% | 83% | 93% | 86% | 88% | 87% | 88% | 78% | 88% | 96% | 85% | 81% | 70% | 81% | 79% | 44% | |
| 66.1% | 75% | 65% | 75% | 69% | 74% | 62% | 63% | 63% | 60% | 65% | 72% | 59% | 55% | 62% | 70% | 74% | 69% | 53% | 73% | 66% | 65% | |
| 82.7% | 84% | 84% | 74% | 79% | 84% | 78% | 84% | 89% | 81% | 80% | 89% | 83% | 87% | 92% | 69% | 71% | 87% | 78% | 91% | 80% | 92% |