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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 11th 79.5% | 9th 80.3% | 14th 77.3% | 17th 76.3% | 19th 72.5% | 18th 73.5% | 16th 77.0% | 20th 72.0% | 12th 78.8% | 13th 78.3% | 2nd 82.8% | 21st 67.5% | 5th 81.5% | 7th 81.0% | 1st 83.3% | 6th 81.3% | 14th 77.3% | 2nd 82.8% | 9th 80.3% | 8th 80.8% | 4th 81.8% | |
| 76.3% | 79% | 75% | 71% | 75% | 73% | 61% | 78% | 76% | 79% | 73% | 86% | 58% | 83% | 89% | 74% | 82% | 80% | 78% | 77% | 81% | 75% | |
| 71.9% | 62% | 78% | 63% | 69% | 64% | 70% | 75% | 64% | 64% | 69% | 78% | 58% | 82% | 75% | 84% | 76% | 78% | 76% | 75% | 75% | 75% | |
| 87.1% | 93% | 91% | 91% | 84% | 83% | 86% | 84% | 77% | 97% | 93% | 83% | 83% | 84% | 86% | 91% | 89% | 79% | 93% | 91% | 90% | 81% | |
| 78.0% | 84% | 77% | 84% | 77% | 70% | 77% | 71% | 71% | 75% | 78% | 84% | 71% | 77% | 74% | 84% | 78% | 72% | 84% | 78% | 77% | 96% |