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 | 6th 79.0% | 3rd 81.5% | 12th 77.3% | 10th 78.0% | 5th 79.0% | 1st 83.0% | 9th 78.2% | 19th 73.5% | 7th 78.8% | 16th 76.0% | 10th 78.0% | 7th 78.8% | 18th 74.3% | 13th 76.8% | 4th 79.8% | 2nd 82.0% | 17th 75.8% | 15th 76.3% | 14th 76.5% | 21st 68.8% | 20th 73.0% | |
| 73.2% | 73% | 76% | 72% | 72% | 77% | 74% | 77% | 73% | 78% | 76% | 75% | 76% | 80% | 77% | 66% | 75% | 72% | 64% | 70% | 64% | 70% | |
| 78.9% | 75% | 78% | 80% | 76% | 81% | 81% | 84% | 73% | 72% | 78% | 85% | 84% | 77% | 83% | 80% | 84% | 77% | 77% | 78% | 77% | 76% | |
| 72.0% | 78% | 79% | 75% | 79% | 73% | 84% | 70% | 61% | 74% | 69% | 62% | 72% | 59% | 62% | 85% | 81% | 72% | 76% | 71% | 62% | 67% | |
| 85.3% | 90% | 93% | 82% | 85% | 85% | 93% | 82% | 87% | 91% | 81% | 90% | 83% | 81% | 85% | 88% | 88% | 82% | 88% | 87% | 72% | 79% |