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 Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | Qwen3 30b A3B Instruct 2507 | Qwen3 Next 80b A3B Instruct | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 7th 61.3% | 11th 60.0% | 3rd 64.7% | 1st 69.7% | 12th 57.0% | 5th 63.0% | 6th 62.3% | 10th 60.3% | 4th 63.7% | 13th 51.7% | 7th 61.3% | 2nd 69.0% | 7th 61.3% | |
| 57.5% | 51% | 52% | 59% | 78% | 53% | 61% | 65% | 66% | 59% | 38% | 57% | 52% | 57% | |
| 41.9% | 42% | 42% | 49% | 44% | 41% | 42% | 35% | 36% | 49% | 37% | 43% | 43% | ||
| 84.3% | 91% | 86% | 86% | 87% | 77% | 86% | 87% | 79% | 83% | 80% | 84% | 86% | 84% |