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 GD2 (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 | 7th 82.0% | 4th 82.7% | 14th 79.0% | 9th 81.3% | 14th 79.0% | 13th 79.3% | 6th 82.3% | 17th 78.0% | 1st 84.7% | 7th 82.0% | 5th 82.3% | 2nd 84.0% | 16th 78.3% | 12th 79.7% | 18th 77.3% | 10th 80.7% | 11th 80.0% | 20th 74.0% | 3rd 83.3% | 19th 76.7% | 21st 72.0% | |
| 91.1% | 96% | 93% | 92% | 92% | 87% | 87% | 97% | 95% | 97% | 90% | 92% | 95% | 91% | 90% | 94% | 94% | 93% | 76% | 96% | 79% | 87% | |
| 70.3% | 73% | 72% | 72% | 75% | 70% | 75% | 70% | 56% | 68% | 70% | 74% | 69% | 63% | 64% | 70% | 78% | 74% | 70% | 73% | 74% | 66% | |
| 78.4% | 77% | 83% | 73% | 77% | 80% | 76% | 80% | 83% | 89% | 86% | 81% | 88% | 81% | 85% | 68% | 70% | 73% | 76% | 81% | 77% | 63% |