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 | 13th 81.8% | 1st 87.0% | 16th 81.0% | 14th 81.7% | 17th 80.3% | 19th 78.8% | 4th 85.0% | 20th 77.3% | 10th 82.5% | 3rd 86.0% | 5th 85.0% | 11th 82.3% | 6th 84.8% | 11th 82.3% | 18th 80.0% | 8th 83.3% | 15th 81.3% | 21st 77.3% | 2nd 86.5% | 9th 83.0% | 7th 83.8% | |
| 75.5% | 75% | 74% | 68% | 65% | 74% | 70% | 75% | 78% | 78% | 81% | 79% | 82% | 78% | 87% | 66% | 73% | 77% | 73% | 75% | 77% | 80% | |
| 84.9% | 77% | 90% | 76% | 85% | 88% | 81% | 92% | 76% | 82% | 88% | 88% | 87% | 90% | 83% | 84% | 89% | 88% | 85% | 89% | 82% | 82% | |
| 77.0% | 76% | 85% | 86% | 82% | 75% | 74% | 75% | 68% | 76% | 81% | 76% | 71% | 78% | 71% | 73% | 82% | 72% | 77% | 84% | 77% | 79% | |
| 92.2% | 99% | 99% | 94% | 95% | 84% | 90% | 98% | 87% | 94% | 94% | 97% | 89% | 93% | 88% | 97% | 89% | 88% | 74% | 98% | 96% | 94% |