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 GD2 (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 | 8th 69.0% | 6th 70.3% | 9th 69.0% | 10th 68.3% | 1st 79.7% | 19th 63.3% | 16th 66.0% | 21st 62.3% | 12th 66.7% | 7th 69.3% | 12th 66.7% | 19th 63.3% | 11th 67.0% | 5th 70.7% | 17th 65.7% | 12th 66.7% | 2nd 73.0% | 12th 66.7% | 4th 71.0% | 18th 65.0% | 3rd 72.3% | |
| 62.5% | 59% | 58% | 59% | 59% | 69% | 54% | 74% | 61% | 62% | 68% | 59% | 68% | 62% | 66% | 54% | 58% | 62% | 56% | 68% | 62% | 75% | |
| 54.2% | 55% | 62% | 62% | 62% | 78% | 59% | 40% | 42% | 47% | 54% | 49% | 40% | 47% | 54% | 66% | 59% | 57% | 48% | 59% | 47% | 52% | |
| 87.8% | 93% | 91% | 86% | 84% | 92% | 77% | 84% | 84% | 91% | 86% | 92% | 82% | 92% | 92% | 77% | 83% | 100% | 96% | 86% | 86% | 90% |