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 | 9th 79.5% | 1st 82.8% | 14th 77.5% | 17th 76.3% | 19th 74.5% | 17th 76.3% | 13th 77.8% | 20th 72.5% | 12th 78.3% | 11th 78.8% | 4th 80.8% | 21st 66.8% | 2nd 82.0% | 5th 80.5% | 3rd 81.0% | 7th 80.0% | 10th 79.5% | 16th 76.5% | 6th 80.0% | 15th 77.0% | 8th 79.7% | |
| 76.5% | 79% | 79% | 71% | 75% | 73% | 72% | 78% | 76% | 74% | 78% | 84% | 75% | 85% | 87% | 67% | 69% | 81% | 75% | 77% | 75% | ||
| 71.8% | 62% | 78% | 69% | 69% | 70% | 70% | 75% | 67% | 64% | 66% | 78% | 58% | 82% | 75% | 76% | 74% | 72% | 77% | 75% | 75% | 75% | |
| 85.7% | 93% | 91% | 91% | 84% | 84% | 86% | 84% | 77% | 97% | 93% | 83% | 67% | 84% | 86% | 97% | 93% | 81% | 82% | 91% | 84% | 72% | |
| 78.0% | 84% | 83% | 79% | 77% | 71% | 77% | 74% | 70% | 78% | 78% | 78% | 67% | 77% | 74% | 84% | 84% | 84% | 72% | 77% | 72% | 97% |