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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 15th 83.0% | 10th 85.0% | 16th 81.8% | 4th 86.8% | 20th 78.8% | 17th 81.5% | 9th 85.0% | 21st 76.0% | 18th 81.0% | 14th 83.8% | 5th 86.3% | 19th 79.0% | 7th 86.0% | 5th 86.3% | 1st 88.3% | 2nd 87.8% | 11th 84.5% | 12th 84.5% | 3rd 87.3% | 13th 84.0% | 8th 85.8% | |
| 77.7% | 74% | 74% | 72% | 72% | 74% | 69% | 72% | 80% | 78% | 77% | 83% | 79% | 84% | 88% | 77% | 79% | 80% | 77% | 81% | 83% | 78% | |
| 84.4% | 79% | 85% | 74% | 88% | 83% | 80% | 92% | 73% | 76% | 84% | 88% | 86% | 85% | 84% | 94% | 90% | 86% | 89% | 83% | 80% | 93% | |
| 79.6% | 80% | 89% | 89% | 89% | 79% | 80% | 77% | 68% | 75% | 80% | 79% | 56% | 76% | 78% | 86% | 87% | 74% | 82% | 87% | 82% | 78% | |
| 94.0% | 99% | 92% | 92% | 98% | 79% | 97% | 99% | 83% | 95% | 94% | 95% | 95% | 99% | 95% | 96% | 95% | 98% | 90% | 98% | 91% | 94% |