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 China. 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 | 1st 93.0% | 7th 89.0% | 4th 91.5% | 8th 88.8% | 12th 80.8% | 9th 86.3% | 11th 85.8% | 4th 91.5% | 3rd 91.8% | 13th 79.8% | 10th 86.0% | 6th 90.3% | 2nd 93.0% | |
| 85.1% | 98% | 87% | 87% | 90% | 63% | 82% | 81% | 93% | 96% | 59% | 92% | 88% | 90% | |
| 89.3% | 94% | 91% | 91% | 88% | 86% | 87% | 83% | 90% | 92% | 88% | 87% | 90% | 94% | |
| 86.4% | 89% | 89% | 91% | 91% | 86% | 85% | 83% | 87% | 83% | 79% | 79% | 92% | 89% | |
| 92.2% | 91% | 89% | 97% | 86% | 88% | 91% | 96% | 96% | 96% | 93% | 86% | 91% | 99% |