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 | 14th 64.0% | 16th 62.0% | 12th 64.3% | 7th 67.0% | 5th 67.3% | 19th 60.0% | 6th 67.0% | 11th 64.3% | 12th 64.3% | 15th 63.0% | 3rd 68.7% | 9th 65.0% | 8th 66.3% | 2nd 70.7% | 17th 61.3% | 10th 64.7% | 18th 60.7% | 21st 58.7% | 1st 74.7% | 19th 60.0% | 4th 68.0% | |
| 62.8% | 64% | 51% | 60% | 73% | 76% | 53% | 68% | 66% | 65% | 73% | 60% | 62% | 59% | 65% | 65% | 60% | 51% | 53% | 64% | 53% | 78% | |
| 55.2% | 56% | 58% | 61% | 56% | 61% | 58% | 56% | 46% | 52% | 47% | 63% | 54% | 59% | 59% | 53% | 55% | 47% | 45% | 78% | 44% | 52% | |
| 76.5% | 72% | 77% | 72% | 72% | 65% | 69% | 77% | 81% | 76% | 69% | 83% | 79% | 81% | 88% | 66% | 79% | 84% | 78% | 82% | 83% | 74% |