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 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 | 4th 85.8% | 12th 80.0% | 2nd 87.3% | 13th 77.8% | 7th 82.5% | 8th 82.2% | 10th 81.5% | 3rd 86.0% | 5th 85.8% | 9th 82.0% | 11th 80.5% | 1st 88.8% | 6th 84.7% | |
| 76.4% | 74% | 65% | 72% | 74% | 69% | 72% | 80% | 78% | 83% | 80% | 84% | 85% | 77% | |
| 84.7% | 88% | 74% | 88% | 83% | 87% | 93% | 76% | 89% | 90% | 81% | 82% | 85% | 85% | |
| 80.2% | 89% | 89% | 91% | 77% | 80% | 74% | 75% | 82% | 75% | 71% | 73% | 87% | 80% | |
| 92.5% | 92% | 92% | 98% | 77% | 94% | 90% | 95% | 95% | 95% | 96% | 83% | 98% | 97% |