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 Pakistan. 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 82.8% | 6th 82.5% | 2nd 83.7% | 12th 77.5% | 11th 78.0% | 13th 77.3% | 8th 81.2% | 3rd 83.3% | 7th 81.8% | 10th 78.8% | 9th 80.0% | 1st 84.0% | 4th 83.0% | |
| 60.4% | 59% | 54% | 59% | 67% | 54% | 51% | 58% | 59% | 68% | 72% | 67% | 58% | 59% | |
| 89.0% | 86% | 93% | 80% | 89% | 87% | 90% | 97% | 97% | 86% | 76% | 90% | 94% | 92% | |
| 86.9% | 90% | 86% | 99% | 82% | 82% | 84% | 86% | 86% | 82% | 82% | 83% | 99% | 89% | |
| 87.9% | 96% | 97% | 97% | 72% | 89% | 84% | 84% | 91% | 91% | 85% | 80% | 85% | 92% |