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 Suburban. 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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 5th 80.0% | 4th 80.3% | 8th 78.7% | 5th 80.0% | 12th 78.3% | 1st 84.0% | 10th 78.3% | 20th 74.7% | 3rd 81.0% | 13th 78.0% | 8th 78.7% | 10th 78.3% | 19th 76.0% | 18th 76.0% | 7th 79.0% | 2nd 82.3% | 16th 77.0% | 14th 77.3% | 14th 77.3% | 21st 67.3% | 17th 76.7% | |
| 87.3% | 91% | 91% | 88% | 88% | 85% | 91% | 85% | 90% | 92% | 84% | 94% | 86% | 84% | 88% | 92% | 89% | 85% | 85% | 86% | 75% | 85% | |
| 69.0% | 71% | 70% | 71% | 76% | 70% | 82% | 68% | 56% | 70% | 70% | 61% | 68% | 59% | 59% | 78% | 79% | 69% | 73% | 68% | 60% | 72% | |
| 77.8% | 78% | 80% | 77% | 76% | 80% | 79% | 82% | 78% | 81% | 80% | 81% | 81% | 85% | 81% | 67% | 79% | 77% | 74% | 78% | 67% | 73% |