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 South Africa. Source: Global Dialogues GD1 (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 | 5th 76.8% | 7th 75.3% | 4th 77.0% | 12th 65.8% | 12th 65.8% | 8th 75.0% | 9th 73.5% | 6th 76.0% | 3rd 78.5% | 11th 70.5% | 10th 72.2% | 1st 80.5% | 2nd 79.5% | |
| 67.0% | 69% | 60% | 69% | 64% | 54% | 61% | 66% | 73% | 77% | 70% | 70% | 67% | 71% | |
| 79.5% | 77% | 78% | 84% | 77% | 71% | 80% | 77% | 85% | 82% | 77% | 77% | 85% | 84% | |
| 69.8% | 75% | 78% | 71% | 71% | 59% | 76% | 71% | 66% | 71% | 57% | 64% | 78% | 71% | |
| 80.9% | 86% | 85% | 84% | 51% | 79% | 83% | 80% | 80% | 84% | 78% | 78% | 92% | 92% |