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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 8th 72.8% | 3rd 77.0% | 16th 69.5% | 12th 70.3% | 1st 81.5% | 21st 66.5% | 17th 69.3% | 20th 67.5% | 5th 74.3% | 9th 72.0% | 2nd 77.8% | 17th 69.3% | 15th 70.0% | 4th 75.3% | 6th 73.8% | 10th 71.5% | 11th 71.0% | 12th 70.3% | 7th 73.5% | 19th 68.8% | 12th 70.3% | |
| 66.0% | 69% | 65% | 58% | 54% | 71% | 54% | 65% | 76% | 69% | 59% | 77% | 69% | 67% | 77% | 65% | 59% | 70% | 77% | 63% | 67% | 55% | |
| 81.8% | 85% | 88% | 77% | 79% | 85% | 86% | 87% | 60% | 81% | 89% | 94% | 73% | 88% | 89% | 79% | 83% | 89% | 73% | 88% | 72% | 72% | |
| 58.0% | 60% | 74% | 65% | 65% | 82% | 48% | 47% | 50% | 64% | 56% | 62% | 47% | 47% | 47% | 67% | 66% | 42% | 44% | 61% | 52% | 72% | |
| 82.2% | 77% | 81% | 78% | 83% | 88% | 78% | 78% | 84% | 83% | 84% | 78% | 88% | 78% | 88% | 84% | 78% | 83% | 87% | 82% | 84% | 82% |