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 | 2nd 71.7% | 14th 62.0% | 13th 62.7% | 9th 66.0% | 6th 66.3% | 19th 57.7% | 5th 67.0% | 11th 64.3% | 14th 62.0% | 18th 60.0% | 3rd 69.3% | 6th 66.3% | 12th 64.0% | 4th 69.0% | 17th 61.3% | 10th 64.7% | 19th 57.7% | 14th 62.0% | 1st 72.7% | 8th 66.3% | 21st 56.0% | |
| 63.4% | 70% | 51% | 60% | 70% | 80% | 53% | 68% | 66% | 65% | 64% | 60% | 62% | 59% | 65% | 74% | 64% | 59% | 60% | 64% | 64% | 53% | |
| 54.8% | 63% | 58% | 61% | 56% | 54% | 52% | 56% | 46% | 45% | 47% | 58% | 54% | 51% | 59% | 52% | 63% | 47% | 47% | 78% | 51% | 53% | |
| 74.5% | 82% | 77% | 67% | 72% | 65% | 68% | 77% | 81% | 76% | 69% | 90% | 83% | 82% | 83% | 58% | 67% | 67% | 79% | 76% | 84% | 62% |