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 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 | 14th 81.5% | 3rd 87.0% | 14th 81.5% | 17th 81.0% | 18th 80.5% | 20th 80.0% | 5th 85.0% | 21st 79.3% | 10th 82.5% | 7th 84.3% | 9th 83.8% | 12th 82.0% | 2nd 87.3% | 14th 81.5% | 6th 84.7% | 13th 81.8% | 7th 84.3% | 11th 82.3% | 1st 88.0% | 19th 80.0% | 4th 85.3% | |
| 76.4% | 72% | 74% | 68% | 65% | 75% | 72% | 75% | 82% | 78% | 78% | 81% | 83% | 89% | 86% | 69% | 76% | 76% | 73% | 80% | 73% | 80% | |
| 85.4% | 81% | 90% | 78% | 82% | 77% | 84% | 92% | 79% | 82% | 88% | 85% | 86% | 92% | 83% | 86% | 87% | 87% | 89% | 90% | 83% | 92% | |
| 77.3% | 76% | 85% | 86% | 82% | 79% | 74% | 76% | 69% | 76% | 79% | 74% | 69% | 74% | 69% | 87% | 71% | 77% | 78% | 84% | 80% | 79% | |
| 92.9% | 97% | 99% | 94% | 95% | 91% | 90% | 97% | 87% | 94% | 92% | 95% | 90% | 94% | 88% | 97% | 93% | 97% | 89% | 98% | 84% | 90% |