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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 83.7% | 6th 82.7% | 12th 80.7% | 9th 81.3% | 19th 77.7% | 14th 80.0% | 3rd 83.7% | 20th 76.7% | 1st 86.0% | 7th 82.0% | 2nd 84.0% | 15th 80.0% | 18th 78.0% | 7th 82.0% | 21st 75.0% | 9th 81.3% | 17th 79.0% | 9th 81.3% | 5th 83.0% | 15th 80.0% | 13th 80.3% | |
| 92.2% | 96% | 93% | 92% | 92% | 90% | 87% | 97% | 91% | 97% | 93% | 99% | 90% | 91% | 95% | 89% | 87% | 92% | 89% | 95% | 94% | 87% | |
| 70.1% | 76% | 72% | 73% | 75% | 63% | 77% | 70% | 56% | 72% | 71% | 72% | 69% | 62% | 66% | 73% | 70% | 68% | 74% | 72% | 65% | 76% | |
| 80.3% | 79% | 83% | 77% | 77% | 80% | 76% | 84% | 83% | 89% | 82% | 81% | 81% | 81% | 85% | 63% | 87% | 77% | 81% | 82% | 81% | 78% |