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 87.5% | 9th 78.8% | 5th 82.8% | 12th 74.8% | 8th 80.0% | 11th 77.0% | 10th 78.5% | 7th 80.3% | 4th 83.3% | 13th 72.5% | 6th 81.0% | 3rd 84.2% | 1st 90.5% | |
| 87.2% | 99% | 82% | 89% | 83% | 77% | 81% | 90% | 78% | 92% | 77% | 96% | 97% | 93% | |
| 88.0% | 98% | 78% | 88% | 72% | 91% | 91% | 76% | 93% | 91% | 90% | 87% | 91% | 98% | |
| 68.5% | 74% | 74% | 73% | 67% | 74% | 62% | 67% | 68% | 68% | 51% | 67% | 72% | 74% | |
| 79.6% | 79% | 81% | 81% | 77% | 78% | 74% | 81% | 82% | 82% | 72% | 74% | 77% | 97% |