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 GD2 (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 | 16th 68.3% | 13th 69.7% | 11th 70.7% | 13th 69.7% | 1st 77.3% | 17th 67.3% | 6th 72.3% | 2nd 75.3% | 8th 72.0% | 12th 69.7% | 9th 71.0% | 3rd 75.0% | 15th 68.7% | 7th 72.0% | 9th 71.0% | 19th 65.7% | 18th 66.3% | 21st 62.0% | 5th 72.7% | 20th 63.7% | 4th 74.7% | |
| 66.8% | 59% | 58% | 70% | 70% | 80% | 55% | 76% | 70% | 70% | 75% | 64% | 64% | 66% | 64% | 75% | 60% | 60% | 57% | 68% | 68% | 74% | |
| 68.7% | 73% | 74% | 75% | 72% | 75% | 75% | 59% | 72% | 64% | 68% | 66% | 79% | 58% | 69% | 72% | 70% | 59% | 54% | 73% | 57% | 79% | |
| 75.2% | 73% | 77% | 67% | 67% | 77% | 72% | 82% | 84% | 82% | 66% | 83% | 82% | 82% | 83% | 66% | 67% | 80% | 75% | 77% | 66% | 71% |