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 | 6th 73.5% | 1st 77.5% | 8th 73.5% | 15th 71.5% | 2nd 76.5% | 10th 72.5% | 9th 72.8% | 18th 69.0% | 13th 72.2% | 20th 67.3% | 3rd 76.3% | 6th 73.5% | 12th 72.3% | 3rd 76.3% | 17th 70.0% | 14th 72.0% | 16th 70.5% | 5th 74.8% | 10th 72.5% | 21st 64.3% | 19th 68.5% | |
| 72.5% | 74% | 75% | 71% | 67% | 77% | 65% | 77% | 80% | 79% | 63% | 77% | 80% | 78% | 83% | 57% | 67% | 72% | 69% | 71% | 70% | 71% | |
| 65.5% | 64% | 76% | 63% | 63% | 75% | 67% | 69% | 50% | 61% | 61% | 68% | 68% | 68% | 71% | 63% | 66% | 67% | 77% | 68% | 50% | 61% | |
| 79.2% | 79% | 82% | 88% | 88% | 84% | 83% | 77% | 74% | 77% | 75% | 82% | 78% | 75% | 76% | 83% | 82% | 71% | 76% | 82% | 70% | 82% | |
| 71.7% | 77% | 77% | 72% | 68% | 70% | 75% | 68% | 72% | 72% | 70% | 78% | 68% | 68% | 75% | 77% | 73% | 72% | 77% | 69% | 67% | 60% |