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 | 2nd 66.7% | 8th 61.3% | 12th 60.0% | 4th 64.7% | 1st 67.0% | 18th 56.7% | 6th 62.3% | 9th 60.7% | 6th 62.3% | 10th 60.3% | 5th 63.7% | 21st 50.3% | 13th 59.7% | 15th 59.0% | 10th 60.3% | 13th 59.7% | 19th 55.7% | 20th 53.0% | 3rd 65.7% | 17th 57.0% | 16th 57.3% | |
| 55.7% | 66% | 51% | 52% | 59% | 74% | 53% | 61% | 66% | 65% | 66% | 59% | 45% | 59% | 57% | 59% | 52% | 52% | 43% | 52% | 39% | 40% | |
| 40.8% | 42% | 42% | 42% | 49% | 44% | 40% | 42% | 36% | 35% | 36% | 49% | 37% | 34% | 36% | 39% | 40% | 23% | 36% | 62% | 40% | 52% | |
| 84.0% | 92% | 91% | 86% | 86% | 83% | 77% | 84% | 80% | 87% | 79% | 83% | 69% | 86% | 84% | 83% | 87% | 92% | 80% | 83% | 92% | 80% |