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 | 12th 77.3% | 5th 81.8% | 12th 77.3% | 15th 76.3% | 18th 75.5% | 19th 73.5% | 17th 75.8% | 20th 73.0% | 10th 79.0% | 9th 79.3% | 1st 82.5% | 15th 76.3% | 8th 80.0% | 7th 80.3% | 11th 78.5% | 6th 81.0% | 1st 82.5% | 12th 77.3% | 3rd 82.3% | 20th 73.0% | 4th 82.0% | |
| 76.7% | 74% | 79% | 71% | 75% | 78% | 61% | 74% | 76% | 77% | 78% | 85% | 75% | 83% | 89% | 55% | 79% | 86% | 80% | 88% | 73% | 75% | |
| 72.0% | 60% | 78% | 63% | 69% | 70% | 70% | 74% | 67% | 64% | 69% | 78% | 76% | 76% | 72% | 78% | 74% | 77% | 76% | 72% | 75% | 75% | |
| 85.6% | 91% | 91% | 91% | 84% | 83% | 86% | 84% | 77% | 97% | 93% | 83% | 83% | 84% | 86% | 84% | 93% | 83% | 81% | 91% | 72% | 81% | |
| 78.8% | 84% | 79% | 84% | 77% | 71% | 77% | 71% | 72% | 78% | 77% | 84% | 71% | 77% | 74% | 97% | 78% | 84% | 72% | 78% | 72% | 97% |