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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 16th 80.3% | 1st 87.0% | 14th 81.3% | 16th 80.3% | 18th 79.8% | 19th 79.3% | 7th 84.7% | 21st 78.5% | 15th 81.2% | 5th 85.3% | 4th 85.5% | 10th 82.5% | 2nd 86.3% | 12th 82.3% | 9th 83.0% | 8th 84.2% | 10th 82.5% | 19th 79.3% | 6th 84.8% | 13th 81.7% | 3rd 86.0% | |
| 76.1% | 72% | 74% | 68% | 64% | 76% | 72% | 75% | 81% | 73% | 80% | 80% | 83% | 83% | 86% | 67% | 79% | 77% | 69% | 75% | 82% | 82% | |
| 85.4% | 75% | 90% | 76% | 82% | 77% | 81% | 91% | 76% | 82% | 88% | 89% | 88% | 95% | 86% | 89% | 90% | 85% | 84% | 90% | 87% | 92% | |
| 76.5% | 77% | 85% | 86% | 82% | 81% | 74% | 76% | 69% | 76% | 80% | 76% | 69% | 73% | 69% | 79% | 74% | 71% | 76% | 76% | 76% | 81% | |
| 93.2% | 97% | 99% | 95% | 93% | 85% | 90% | 97% | 88% | 94% | 93% | 97% | 90% | 94% | 88% | 97% | 94% | 97% | 88% | 98% | 89% |