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 | 5th 82.0% | 9th 79.3% | 4th 82.3% | 11th 75.0% | 13th 74.7% | 11th 75.0% | 10th 78.0% | 6th 81.7% | 3rd 83.0% | 8th 81.0% | 7th 81.0% | 2nd 83.0% | 1st 84.3% | |
| 93.1% | 93% | 92% | 96% | 82% | 96% | 96% | 91% | 95% | 95% | 95% | 92% | 98% | 89% | |
| 68.9% | 74% | 77% | 68% | 67% | 69% | 61% | 69% | 73% | 68% | 62% | 61% | 70% | 77% | |
| 78.1% | 79% | 69% | 83% | 76% | 59% | 68% | 74% | 77% | 86% | 86% | 90% | 81% | 87% |