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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 5th 74.3% | 1st 77.0% | 8th 72.8% | 12th 72.5% | 1st 77.0% | 4th 75.3% | 8th 72.8% | 18th 68.5% | 13th 71.8% | 19th 67.5% | 3rd 75.8% | 6th 73.8% | 15th 71.0% | 8th 72.8% | 13th 71.8% | 16th 70.3% | 17th 70.0% | 7th 73.3% | 8th 72.8% | 21st 62.5% | 20th 62.7% | |
| 73.0% | 73% | 75% | 67% | 67% | 79% | 68% | 79% | 78% | 77% | 66% | 80% | 81% | 78% | 81% | 68% | 69% | 78% | 78% | 71% | 59% | 60% | |
| 65.3% | 67% | 68% | 63% | 63% | 75% | 72% | 69% | 50% | 61% | 61% | 68% | 72% | 71% | 68% | 65% | 62% | 67% | 71% | 68% | 59% | 51% | |
| 78.1% | 80% | 88% | 88% | 88% | 84% | 86% | 75% | 74% | 77% | 75% | 77% | 78% | 67% | 72% | 82% | 80% | 67% | 67% | 82% | 74% | 79% | |
| 70.5% | 77% | 77% | 73% | 72% | 70% | 75% | 68% | 72% | 72% | 68% | 78% | 64% | 68% | 70% | 72% | 70% | 68% | 77% | 70% | 58% | 61% |