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 Brazil. 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 | 3rd 83.7% | 8th 81.0% | 6th 82.3% | 12th 75.7% | 11th 76.3% | 12th 75.7% | 10th 78.0% | 9th 80.0% | 4th 83.3% | 7th 82.0% | 5th 83.0% | 1st 84.3% | 1st 84.3% | |
| 93.5% | 98% | 92% | 96% | 82% | 93% | 98% | 89% | 93% | 98% | 94% | 94% | 98% | 90% | |
| 68.8% | 74% | 77% | 68% | 66% | 69% | 62% | 66% | 72% | 66% | 62% | 65% | 70% | 77% | |
| 80.0% | 79% | 74% | 83% | 79% | 67% | 67% | 79% | 75% | 86% | 90% | 90% | 85% | 86% |