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 Korea South. 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 | 2nd 82.0% | 4th 79.5% | 5th 79.0% | 12th 71.0% | 10th 71.8% | 9th 73.8% | 7th 77.3% | 13th 64.8% | 6th 78.8% | 11th 71.2% | 3rd 80.8% | 8th 76.5% | 1st 83.5% | |
| 88.5% | 96% | 81% | 86% | 82% | 80% | 89% | 91% | 70% | 93% | 98% | 98% | 93% | 93% | |
| 82.2% | 87% | 88% | 88% | 72% | 79% | 87% | 80% | 76% | 87% | 69% | 87% | 82% | 86% | |
| 60.2% | 68% | 68% | 68% | 62% | 55% | 51% | 66% | 45% | 54% | 51% | 57% | 63% | 74% | |
| 73.8% | 77% | 81% | 74% | 68% | 73% | 68% | 72% | 68% | 81% | 67% | 81% | 68% | 81% |