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 3.7 Sonnet | Claude Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT 5 | GPT 5.1 | GPT OSS 120b | GPT OSS 20b | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | Grok 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 15th 82.8% | 4th 87.3% | 18th 81.8% | 4th 87.3% | 20th 78.3% | 12th 83.7% | 17th 82.2% | 21st 76.3% | 19th 81.3% | 9th 86.0% | 11th 85.0% | 12th 83.7% | 6th 87.2% | 16th 82.5% | 7th 86.8% | 10th 85.3% | 14th 83.3% | 3rd 87.5% | 1st 88.8% | 7th 86.8% | 2nd 88.5% | |
| 78.1% | 75% | 74% | 72% | 72% | 73% | 72% | 73% | 82% | 80% | 77% | 85% | 82% | 82% | 86% | 79% | 84% | 79% | 80% | 81% | 74% | 79% | |
| 84.9% | 79% | 88% | 74% | 88% | 80% | 87% | 92% | 74% | 75% | 85% | 81% | 86% | 94% | 83% | 87% | 82% | 91% | 91% | 88% | 88% | 89% | |
| 80.7% | 78% | 89% | 89% | 91% | 89% | 80% | 74% | 66% | 75% | 85% | 75% | 71% | 76% | 74% | 83% | 79% | 73% | 83% | 88% | 87% | 90% | |
| 93.8% | 99% | 98% | 92% | 98% | 71% | 96% | 90% | 83% | 95% | 97% | 99% | 96% | 97% | 87% | 98% | 96% | 90% | 96% | 98% | 98% | 96% |