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 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 | 10th 76.3% | 11th 76.0% | 3rd 80.3% | 1st 84.0% | 12th 72.0% | 9th 77.0% | 8th 77.3% | 5th 78.7% | 6th 78.0% | 13th 71.7% | 4th 79.3% | 6th 78.0% | 2nd 82.0% | |
| 81.2% | 77% | 77% | 80% | 98% | 70% | 86% | 83% | 92% | 77% | 83% | 75% | 77% | 80% | |
| 73.5% | 73% | 78% | 82% | 75% | 75% | 72% | 72% | 72% | 72% | 59% | 69% | 78% | 79% | |
| 78.5% | 79% | 73% | 79% | 79% | 71% | 73% | 77% | 72% | 85% | 73% | 94% | 79% | 87% |