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 81.3% | 6th 85.5% | 2nd 86.8% | 12th 82.5% | 18th 80.0% | 19th 79.3% | 4th 86.3% | 8th 84.5% | 21st 77.3% | 8th 84.5% | 1st 93.3% | 11th 83.8% | 5th 86.0% | 13th 82.3% | 10th 84.3% | 15th 81.8% | 13th 82.3% | 17th 80.5% | 6th 85.5% | 3rd 86.3% | 20th 79.0% | |
| 77.2% | 73% | 79% | 74% | 72% | 74% | 72% | 81% | 73% | 77% | 78% | 86% | 75% | 81% | 81% | 77% | 86% | 73% | 73% | 79% | 75% | 82% | |
| 85.8% | 76% | 93% | 90% | 78% | 76% | 81% | 90% | 92% | 76% | 85% | 96% | 88% | 89% | 89% | 89% | 86% | 85% | 84% | 88% | 89% | 82% | |
| 76.3% | 78% | 75% | 85% | 86% | 79% | 74% | 80% | 76% | 69% | 79% | 93% | 78% | 76% | 69% | 76% | 67% | 77% | 68% | 79% | 83% | 56% | |
| 94.5% | 98% | 95% | 98% | 94% | 91% | 90% | 94% | 97% | 87% | 96% | 98% | 94% | 98% | 90% | 95% | 88% | 94% | 97% | 96% | 98% | 96% |