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 76.3% | 7th 80.3% | 13th 77.3% | 20th 73.7% | 18th 74.3% | 16th 75.8% | 19th 73.8% | 21st 72.5% | 12th 77.5% | 10th 79.3% | 3rd 82.8% | 17th 75.3% | 8th 80.0% | 5th 81.0% | 14th 76.3% | 9th 79.5% | 11th 79.0% | 6th 80.8% | 2nd 82.8% | 4th 82.5% | 1st 85.0% | |
| 77.0% | 74% | 75% | 71% | 75% | 78% | 61% | 78% | 81% | 74% | 73% | 86% | 75% | 85% | 89% | 58% | 82% | 83% | 75% | 86% | 83% | 75% | |
| 72.7% | 62% | 78% | 63% | 69% | 66% | 79% | 74% | 64% | 64% | 69% | 78% | 72% | 76% | 75% | 72% | 76% | 84% | 78% | 76% | 77% | 75% | |
| 86.7% | 91% | 91% | 91% | 83% | 86% | 72% | 77% | 97% | 97% | 83% | 83% | 82% | 86% | 91% | 83% | 71% | 93% | 91% | 93% | 93% | ||
| 77.6% | 78% | 77% | 84% | 77% | 70% | 77% | 71% | 68% | 75% | 78% | 84% | 71% | 77% | 74% | 84% | 77% | 78% | 77% | 78% | 77% | 97% |