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 | 15th 76.8% | 2nd 81.5% | 14th 76.8% | 7th 78.0% | 13th 77.0% | 1st 82.8% | 9th 78.0% | 20th 73.8% | 10th 77.5% | 16th 76.3% | 5th 79.3% | 6th 78.3% | 17th 75.3% | 18th 75.0% | 4th 79.3% | 3rd 79.8% | 12th 77.0% | 7th 78.0% | 11th 77.3% | 21st 66.5% | 19th 74.0% | |
| 72.9% | 71% | 76% | 72% | 72% | 71% | 73% | 77% | 74% | 77% | 77% | 75% | 76% | 76% | 77% | 62% | 69% | 72% | 73% | 73% | 67% | 70% | |
| 77.2% | 73% | 78% | 80% | 76% | 81% | 81% | 82% | 73% | 72% | 78% | 85% | 82% | 78% | 76% | 81% | 80% | 76% | 70% | 78% | 68% | 74% | |
| 72.5% | 71% | 79% | 75% | 79% | 70% | 84% | 71% | 61% | 73% | 69% | 71% | 72% | 64% | 62% | 87% | 81% | 72% | 76% | 71% | 62% | 72% | |
| 85.6% | 92% | 93% | 80% | 85% | 86% | 93% | 82% | 87% | 88% | 81% | 86% | 83% | 83% | 85% | 87% | 89% | 88% | 93% | 87% | 69% | 80% |