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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 5th 79.3% | 2nd 81.5% | 10th 77.3% | 8th 78.0% | 10th 77.3% | 1st 83.0% | 17th 76.3% | 19th 73.0% | 6th 78.8% | 16th 76.5% | 3rd 80.0% | 7th 78.5% | 18th 74.8% | 14th 76.8% | 9th 77.8% | 4th 80.0% | 13th 77.0% | 10th 77.3% | 15th 76.8% | 21st 70.0% | 20th 72.3% | |
| 72.3% | 73% | 76% | 72% | 72% | 77% | 74% | 65% | 71% | 78% | 76% | 75% | 76% | 77% | 77% | 65% | 72% | 72% | 72% | 73% | 64% | 62% | |
| 77.9% | 73% | 78% | 80% | 76% | 74% | 81% | 87% | 73% | 73% | 78% | 85% | 84% | 78% | 83% | 76% | 83% | 76% | 73% | 78% | 72% | 74% | |
| 72.2% | 78% | 79% | 75% | 79% | 72% | 84% | 70% | 61% | 74% | 71% | 71% | 72% | 61% | 62% | 82% | 76% | 72% | 76% | 72% | 62% | 68% | |
| 86.5% | 93% | 93% | 82% | 85% | 86% | 93% | 83% | 87% | 90% | 81% | 89% | 82% | 83% | 85% | 88% | 89% | 88% | 88% | 84% | 82% | 85% |