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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 16th 80.5% | 6th 86.5% | 4th 87.0% | 15th 81.0% | 20th 78.0% | 17th 79.5% | 6th 86.5% | 9th 84.7% | 21st 77.0% | 11th 82.5% | 1st 90.0% | 10th 84.0% | 8th 85.5% | 12th 82.0% | 3rd 87.8% | 18th 78.8% | 12th 82.0% | 18th 78.8% | 2nd 88.0% | 5th 87.0% | 14th 81.5% | |
| 77.7% | 74% | 83% | 74% | 68% | 70% | 72% | 83% | 75% | 79% | 78% | 84% | 74% | 80% | 82% | 83% | 86% | 76% | 72% | 84% | 77% | 77% | |
| 84.8% | 74% | 91% | 90% | 76% | 77% | 81% | 89% | 91% | 76% | 82% | 96% | 89% | 89% | 87% | 95% | 73% | 79% | 83% | 90% | 90% | 82% | |
| 77.5% | 76% | 77% | 85% | 86% | 83% | 75% | 80% | 76% | 67% | 76% | 90% | 79% | 76% | 69% | 76% | 67% | 75% | 71% | 79% | 83% | 82% | |
| 93.1% | 98% | 95% | 99% | 94% | 82% | 90% | 94% | 97% | 86% | 94% | 90% | 94% | 97% | 90% | 97% | 89% | 98% | 89% | 99% | 98% | 85% |