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 60.7% | 8th 60.0% | 5th 62.3% | 1st 66.7% | 11th 55.7% | 4th 63.0% | 6th 62.0% | 9th 58.7% | 3rd 63.7% | 12th 54.0% | 10th 57.7% | 2nd 64.3% | 13th 50.0% | |
| 56.9% | 51% | 52% | 52% | 74% | 53% | 61% | 65% | 66% | 59% | 45% | 53% | 52% | 57% | |
| 42.7% | 42% | 42% | 49% | 49% | 37% | 42% | 35% | 36% | 49% | 37% | 36% | 58% | 43% | |
| 82.6% | 89% | 86% | 86% | 77% | 77% | 86% | 86% | 74% | 83% | 80% | 84% | 83% |