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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 14th 77.0% | 5th 81.3% | 13th 77.3% | 16th 76.3% | 21st 68.3% | 17th 73.5% | 15th 76.8% | 19th 72.5% | 10th 79.0% | 11th 78.3% | 6th 80.3% | 19th 72.5% | 11th 78.3% | 3rd 82.3% | 2nd 82.5% | 6th 80.3% | 9th 79.8% | 6th 80.3% | 1st 83.3% | 4th 81.5% | 18th 73.5% | |
| 77.5% | 75% | 79% | 71% | 75% | 64% | 61% | 74% | 76% | 77% | 73% | 83% | 81% | 83% | 89% | 83% | 78% | 83% | 80% | 88% | 80% | 75% | |
| 72.8% | 62% | 78% | 63% | 69% | 64% | 70% | 75% | 64% | 64% | 69% | 78% | 71% | 76% | 77% | 78% | 76% | 76% | 83% | 76% | 84% | 75% | |
| 85.0% | 93% | 91% | 91% | 84% | 83% | 86% | 87% | 77% | 97% | 93% | 82% | 67% | 77% | 86% | 85% | 83% | 83% | 86% | 91% | 90% | 72% | |
| 76.0% | 78% | 77% | 84% | 77% | 62% | 77% | 71% | 73% | 78% | 78% | 78% | 71% | 77% | 77% | 84% | 84% | 77% | 72% | 78% | 72% | 72% |