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 | 12th 68.0% | 5th 70.3% | 11th 68.3% | 3rd 71.3% | 2nd 72.0% | 21st 63.3% | 15th 66.7% | 6th 70.0% | 13th 67.3% | 8th 68.7% | 15th 66.7% | 20th 63.7% | 7th 69.0% | 8th 68.7% | 13th 67.3% | 8th 68.7% | 19th 64.0% | 4th 70.7% | 1st 73.0% | 15th 66.7% | 18th 66.0% | |
| 62.1% | 54% | 58% | 59% | 68% | 65% | 54% | 74% | 68% | 61% | 68% | 59% | 68% | 68% | 66% | 54% | 57% | 54% | 60% | 68% | 61% | 61% | |
| 53.1% | 59% | 62% | 62% | 62% | 59% | 59% | 40% | 42% | 49% | 52% | 49% | 40% | 47% | 54% | 66% | 59% | 45% | 52% | 59% | 52% | 47% | |
| 89.0% | 91% | 91% | 84% | 84% | 92% | 77% | 86% | 100% | 92% | 86% | 92% | 83% | 92% | 86% | 82% | 90% | 93% | 100% | 92% | 87% | 90% |