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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 16th 82.5% | 5th 87.5% | 8th 85.0% | 18th 81.8% | 20th 81.0% | 9th 84.5% | 1st 88.5% | 17th 82.2% | 21st 77.3% | 14th 83.5% | 4th 87.5% | 13th 83.8% | 6th 87.0% | 12th 84.0% | 2nd 88.0% | 19th 81.5% | 11th 84.3% | 9th 84.5% | 7th 85.5% | 3rd 87.8% | 15th 83.3% | |
| 79.4% | 78% | 87% | 74% | 72% | 74% | 72% | 81% | 72% | 81% | 80% | 77% | 77% | 84% | 82% | 85% | 85% | 79% | 78% | 86% | 81% | 82% | |
| 85.0% | 84% | 87% | 85% | 74% | 83% | 90% | 87% | 93% | 77% | 76% | 91% | 84% | 91% | 85% | 94% | 84% | 88% | 85% | 81% | 85% | 82% | |
| 80.5% | 75% | 79% | 89% | 89% | 90% | 80% | 87% | 74% | 68% | 83% | 89% | 80% | 74% | 71% | 75% | 74% | 77% | 81% | 86% | 87% | 82% | |
| 92.4% | 93% | 97% | 92% | 92% | 77% | 96% | 99% | 90% | 83% | 95% | 93% | 94% | 99% | 98% | 98% | 83% | 93% | 94% | 89% | 98% | 87% |