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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 68.3% | 14th 62.0% | 11th 64.3% | 6th 67.0% | 7th 66.0% | 20th 57.7% | 5th 67.0% | 9th 65.7% | 11th 64.3% | 13th 63.0% | 4th 67.7% | 8th 65.7% | 10th 64.7% | 2nd 69.0% | 18th 60.7% | 14th 62.0% | 21st 57.3% | 16th 61.3% | 1st 72.7% | 19th 59.0% | 17th 61.0% | |
| 62.0% | 75% | 51% | 60% | 73% | 75% | 53% | 68% | 70% | 65% | 73% | 60% | 62% | 64% | 65% | 60% | 59% | 48% | 50% | 64% | 53% | 53% | |
| 56.3% | 58% | 58% | 61% | 56% | 61% | 51% | 56% | 46% | 52% | 47% | 63% | 56% | 53% | 59% | 56% | 63% | 45% | 55% | 78% | 48% | 61% | |
| 74.0% | 72% | 77% | 72% | 72% | 62% | 69% | 77% | 81% | 76% | 69% | 80% | 79% | 77% | 83% | 66% | 64% | 79% | 79% | 76% | 76% | 69% |