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 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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 10th 78.5% | 6th 80.3% | 20th 73.0% | 16th 75.5% | 18th 74.0% | 21st 71.0% | 9th 79.0% | 13th 76.8% | 19th 73.0% | 11th 77.0% | 4th 80.5% | 17th 74.5% | 5th 80.5% | 8th 79.3% | 15th 76.0% | 3rd 81.0% | 14th 76.3% | 11th 77.0% | 2nd 82.2% | 7th 79.8% | 1st 88.8% | |
| 72.5% | 75% | 74% | 62% | 58% | 64% | 59% | 67% | 78% | 64% | 66% | 81% | 70% | 81% | 88% | 58% | 74% | 76% | 76% | 76% | 79% | 97% | |
| 79.5% | 70% | 86% | 72% | 79% | 62% | 84% | 87% | 70% | 73% | 76% | 86% | 86% | 86% | 72% | 85% | 78% | 80% | 85% | 85% | 81% | 87% | |
| 72.2% | 83% | 82% | 83% | 77% | 79% | 64% | 69% | 64% | 62% | 78% | 68% | 57% | 69% | 64% | 73% | 80% | 64% | 64% | 78% | 72% | 86% | |
| 87.0% | 86% | 79% | 75% | 88% | 91% | 77% | 93% | 95% | 93% | 88% | 87% | 85% | 86% | 93% | 88% | 92% | 85% | 83% | 90% | 87% | 85% |