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 Urban. 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 82.5% | 8th 85.0% | 18th 81.8% | 6th 87.0% | 20th 81.0% | 9th 84.5% | 17th 82.2% | 21st 77.3% | 14th 83.5% | 13th 83.8% | 5th 87.0% | 12th 84.0% | 3rd 88.0% | 19th 81.5% | 2nd 88.8% | 7th 85.5% | 11th 84.3% | 9th 84.5% | 4th 87.8% | 15th 83.3% | 1st 89.5% | |
| 78.8% | 78% | 74% | 72% | 72% | 74% | 72% | 72% | 81% | 80% | 77% | 84% | 82% | 85% | 85% | 87% | 82% | 79% | 78% | 81% | 82% | 78% | |
| 85.2% | 84% | 85% | 74% | 88% | 83% | 90% | 93% | 77% | 76% | 84% | 91% | 85% | 94% | 84% | 83% | 82% | 88% | 85% | 85% | 82% | 96% | |
| 80.8% | 75% | 89% | 89% | 90% | 90% | 80% | 74% | 68% | 83% | 80% | 74% | 71% | 75% | 74% | 86% | 83% | 77% | 81% | 87% | 82% | 88% | |
| 92.9% | 93% | 92% | 92% | 98% | 77% | 96% | 90% | 83% | 95% | 94% | 99% | 98% | 98% | 83% | 99% | 95% | 93% | 94% | 98% | 87% | 96% |