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 | 8th 75.3% | 7th 75.3% | 4th 77.0% | 11th 71.2% | 13th 66.5% | 5th 76.0% | 10th 71.5% | 3rd 77.7% | 9th 72.5% | 12th 68.8% | 6th 75.5% | 1st 80.0% | 2nd 80.0% | |
| 66.6% | 69% | 60% | 69% | 67% | 54% | 65% | 62% | 72% | 68% | 60% | 81% | 66% | 73% | |
| 79.3% | 77% | 78% | 84% | 77% | 74% | 80% | 73% | 85% | 80% | 78% | 77% | 84% | 84% | |
| 69.4% | 69% | 78% | 71% | 78% | 59% | 76% | 71% | 74% | 59% | 54% | 64% | 78% | 71% | |
| 82.3% | 86% | 85% | 84% | 63% | 79% | 83% | 80% | 80% | 83% | 83% | 80% | 92% | 92% |