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 | 12th 81.0% | 1st 88.0% | 19th 79.0% | 14th 80.8% | 20th 77.8% | 15th 80.0% | 6th 84.3% | 21st 77.5% | 8th 82.5% | 9th 82.3% | 4th 85.8% | 17th 79.5% | 3rd 86.3% | 11th 81.0% | 7th 83.7% | 13th 80.8% | 10th 81.5% | 16th 79.8% | 2nd 86.5% | 18th 79.3% | 5th 85.5% | |
| 74.7% | 74% | 78% | 68% | 65% | 74% | 72% | 73% | 78% | 73% | 77% | 81% | 83% | 85% | 80% | 69% | 68% | 73% | 69% | 77% | 76% | 76% | |
| 84.9% | 75% | 90% | 76% | 82% | 77% | 84% | 91% | 76% | 85% | 80% | 88% | 89% | 91% | 86% | 86% | 89% | 86% | 88% | 89% | 79% | 95% | |
| 75.4% | 77% | 85% | 86% | 82% | 76% | 74% | 76% | 67% | 76% | 79% | 76% | 56% | 75% | 71% | 85% | 79% | 68% | 71% | 82% | 68% | ||
| 93.0% | 98% | 99% | 86% | 94% | 84% | 90% | 97% | 89% | 96% | 93% | 98% | 90% | 94% | 87% | 95% | 87% | 99% | 91% | 98% | 94% |