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 Italy. 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 | 9th 73.8% | 2nd 77.0% | 13th 71.2% | 16th 70.3% | 10th 73.5% | 19th 68.0% | 15th 70.5% | 17th 68.3% | 7th 74.3% | 17th 68.3% | 1st 77.8% | 20th 67.0% | 11th 73.0% | 4th 76.0% | 12th 72.7% | 8th 74.0% | 5th 74.8% | 6th 74.5% | 3rd 76.5% | 14th 70.5% | 21st 66.0% | |
| 66.6% | 71% | 65% | 65% | 54% | 70% | 60% | 63% | 73% | 69% | 57% | 77% | 69% | 70% | 77% | 60% | 63% | 77% | 69% | 70% | 62% | 58% | |
| 82.8% | 87% | 88% | 77% | 79% | 77% | 86% | 87% | 66% | 81% | 79% | 89% | 73% | 88% | 86% | 76% | 86% | 89% | 86% | 91% | 89% | 79% | |
| 58.0% | 60% | 74% | 65% | 65% | 58% | 48% | 47% | 50% | 64% | 53% | 62% | 47% | 57% | 53% | 67% | 68% | 51% | 60% | 61% | 53% | 54% | |
| 81.7% | 77% | 81% | 78% | 83% | 89% | 78% | 85% | 84% | 83% | 84% | 83% | 79% | 77% | 88% | 88% | 79% | 82% | 83% | 84% | 78% | 73% |