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 | 15th 76.3% | 3rd 82.8% | 12th 77.3% | 16th 76.0% | 20th 71.5% | 18th 73.5% | 13th 76.8% | 19th 73.3% | 9th 80.0% | 17th 75.8% | 5th 81.5% | 21st 66.8% | 10th 80.0% | 7th 80.3% | 2nd 83.5% | 6th 80.5% | 11th 77.8% | 14th 76.5% | 7th 80.3% | 1st 86.8% | 4th 82.7% | |
| 77.0% | 79% | 79% | 71% | 71% | 73% | 61% | 78% | 82% | 81% | 66% | 88% | 75% | 83% | 89% | 83% | 82% | 80% | 62% | 77% | 81% | 75% | |
| 71.3% | 60% | 78% | 63% | 72% | 64% | 70% | 74% | 64% | 64% | 66% | 78% | 58% | 76% | 72% | 76% | 70% | 77% | 76% | 75% | 77% | 87% | |
| 85.8% | 91% | 91% | 91% | 84% | 83% | 86% | 84% | 77% | 97% | 93% | 82% | 67% | 84% | 86% | 91% | 92% | 82% | 84% | 91% | 93% | 72% | |
| 78.3% | 75% | 83% | 84% | 77% | 66% | 77% | 71% | 70% | 78% | 78% | 78% | 67% | 77% | 74% | 84% | 78% | 72% | 84% | 78% | 96% | 97% |