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 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 | 4th 80.3% | 11th 73.0% | 2nd 82.3% | 10th 75.0% | 13th 66.3% | 9th 75.3% | 5th 80.0% | 5th 80.0% | 3rd 81.3% | 12th 70.3% | 7th 79.3% | 8th 78.7% | 1st 83.0% | |
| 89.0% | 94% | 73% | 90% | 92% | 76% | 90% | 93% | 96% | 93% | 79% | 93% | 93% | 95% | |
| 83.1% | 86% | 84% | 89% | 82% | 77% | 82% | 84% | 82% | 81% | 76% | 83% | 84% | 90% | |
| 59.8% | 61% | 62% | 68% | 51% | 46% | 54% | 63% | 62% | 70% | 56% | 62% | 59% | 64% |