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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 5th 80.3% | 1st 84.3% | 14th 76.7% | 6th 80.0% | 8th 78.7% | 2nd 83.7% | 9th 78.3% | 16th 76.0% | 4th 81.3% | 9th 78.3% | 9th 78.3% | 9th 78.3% | 17th 75.7% | 14th 76.7% | 18th 75.0% | 3rd 83.3% | 19th 73.0% | 7th 79.0% | 13th 77.0% | 20th 72.7% | 21st 70.7% | |
| 87.7% | 91% | 91% | 82% | 88% | 85% | 91% | 85% | 90% | 93% | 84% | 96% | 86% | 84% | 88% | 84% | 90% | 85% | 92% | 89% | 87% | 80% | |
| 69.0% | 75% | 82% | 71% | 76% | 70% | 82% | 68% | 56% | 71% | 70% | 60% | 68% | 61% | 61% | 77% | 79% | 58% | 69% | 68% | 59% | 69% | |
| 77.2% | 75% | 80% | 77% | 76% | 81% | 78% | 82% | 82% | 80% | 81% | 79% | 81% | 82% | 81% | 64% | 81% | 76% | 76% | 74% | 72% | 63% |