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 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 | 6th 84.0% | 2nd 86.3% | 19th 78.7% | 12th 81.7% | 18th 78.7% | 13th 81.0% | 9th 82.7% | 16th 79.0% | 1st 88.7% | 8th 83.3% | 4th 85.3% | 9th 82.7% | 15th 79.7% | 14th 80.3% | 9th 82.7% | 5th 85.0% | 6th 84.0% | 16th 79.0% | 3rd 85.7% | 20th 77.7% | 21st 77.3% | |
| 91.7% | 96% | 96% | 84% | 93% | 90% | 88% | 99% | 90% | 98% | 94% | 98% | 91% | 93% | 88% | 88% | 97% | 97% | 86% | 96% | 83% | 80% | |
| 74.8% | 75% | 82% | 77% | 77% | 70% | 82% | 73% | 64% | 77% | 74% | 77% | 73% | 64% | 67% | 77% | 79% | 78% | 78% | 75% | 77% | 74% | |
| 79.8% | 81% | 81% | 75% | 75% | 76% | 73% | 76% | 83% | 91% | 82% | 81% | 84% | 82% | 86% | 83% | 79% | 77% | 73% | 86% | 73% | 78% |