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 Urban. 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 | 1st 86.3% | 12th 79.7% | 9th 81.7% | 11th 80.0% | 12th 79.7% | 6th 84.0% | 3rd 86.0% | 8th 82.3% | 1st 86.3% | 7th 83.0% | 10th 81.0% | 5th 84.3% | 3rd 86.0% | |
| 93.0% | 96% | 84% | 93% | 90% | 88% | 99% | 98% | 93% | 98% | 90% | 90% | 96% | 94% | |
| 75.4% | 82% | 77% | 77% | 72% | 79% | 73% | 69% | 74% | 77% | 75% | 67% | 77% | 81% | |
| 80.9% | 81% | 78% | 75% | 78% | 72% | 80% | 91% | 80% | 84% | 84% | 86% | 80% | 83% |