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 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 | 6th 81.0% | 2nd 83.3% | 7th 79.7% | 11th 78.3% | 10th 79.3% | 4th 81.3% | 19th 75.0% | 14th 77.0% | 13th 77.3% | 17th 76.3% | 12th 77.7% | 9th 79.7% | 14th 77.0% | 16th 76.7% | 4th 81.3% | 3rd 81.3% | 17th 76.3% | 1st 85.7% | 7th 79.7% | 21st 70.3% | 20th 74.0% | |
| 87.0% | 92% | 92% | 86% | 83% | 85% | 92% | 86% | 88% | 89% | 85% | 90% | 86% | 84% | 89% | 86% | 91% | 90% | 90% | 86% | 80% | 78% | |
| 70.0% | 73% | 75% | 76% | 77% | 77% | 77% | 59% | 62% | 66% | 63% | 65% | 71% | 65% | 58% | 83% | 73% | 61% | 84% | 72% | 65% | 69% | |
| 78.4% | 78% | 83% | 77% | 75% | 76% | 75% | 80% | 81% | 77% | 81% | 78% | 82% | 82% | 83% | 75% | 80% | 78% | 83% | 81% | 66% | 75% |