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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 8th 79.7% | 1st 83.3% | 9th 79.3% | 5th 80.3% | 11th 78.3% | 4th 81.3% | 17th 75.7% | 14th 77.0% | 10th 78.3% | 16th 76.3% | 13th 77.7% | 7th 80.3% | 19th 74.7% | 12th 78.0% | 2nd 82.0% | 3rd 81.7% | 5th 80.3% | 14th 77.0% | 18th 75.3% | 20th 71.7% | |
| 87.9% | 88% | 92% | 84% | 89% | 85% | 92% | 86% | 88% | 89% | 85% | 90% | 86% | 86% | 89% | 89% | 93% | 90% | 95% | 82% | 80% | |
| 68.9% | 73% | 75% | 76% | 77% | 74% | 77% | 58% | 62% | 66% | 63% | 64% | 73% | 60% | 63% | 73% | 78% | 73% | 57% | 72% | 64% | |
| 78.4% | 78% | 83% | 78% | 75% | 76% | 75% | 83% | 81% | 80% | 81% | 79% | 82% | 78% | 82% | 84% | 74% | 78% | 79% | 72% | 71% |