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 Germany. 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 | 17th 75.5% | 4th 81.3% | 14th 77.3% | 15th 76.3% | 19th 74.5% | 13th 78.0% | 16th 75.8% | 20th 72.5% | 18th 75.3% | 12th 78.3% | 8th 80.5% | 21st 71.5% | 3rd 82.3% | 6th 80.7% | 2nd 84.5% | 10th 79.3% | 11th 79.0% | 9th 79.5% | 4th 81.3% | 1st 86.3% | 6th 80.7% | |
| 78.8% | 71% | 79% | 71% | 75% | 78% | 70% | 74% | 76% | 77% | 73% | 84% | 75% | 92% | 89% | 87% | 82% | 83% | 75% | 84% | 81% | 79% | |
| 71.1% | 60% | 78% | 63% | 69% | 64% | 79% | 74% | 64% | 64% | 69% | 78% | 58% | 76% | 72% | 76% | 76% | 76% | 76% | 72% | 75% | 75% | |
| 85.7% | 93% | 91% | 91% | 84% | 85% | 86% | 84% | 77% | 82% | 93% | 82% | 83% | 84% | 86% | 91% | 82% | 86% | 83% | 91% | 93% | 72% | |
| 78.7% | 78% | 77% | 84% | 77% | 71% | 77% | 71% | 73% | 78% | 78% | 78% | 70% | 77% | 76% | 84% | 77% | 71% | 84% | 78% | 96% | 97% |