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 | 12th 84.5% | 9th 85.0% | 10th 84.8% | 17th 81.8% | 20th 79.0% | 18th 81.3% | 2nd 87.8% | 15th 83.0% | 21st 77.5% | 19th 81.0% | 1st 89.0% | 10th 84.8% | 6th 86.3% | 14th 83.5% | 5th 87.0% | 13th 84.3% | 16th 82.0% | 7th 85.8% | 8th 85.3% | 2nd 87.8% | 4th 87.5% | |
| 79.5% | 77% | 84% | 74% | 72% | 74% | 69% | 81% | 72% | 82% | 80% | 90% | 76% | 84% | 81% | 86% | 86% | 79% | 79% | 85% | 85% | 74% | |
| 84.8% | 83% | 85% | 84% | 74% | 85% | 80% | 88% | 92% | 79% | 74% | 90% | 85% | 88% | 85% | 90% | 82% | 86% | 88% | 86% | 83% | 93% | |
| 79.5% | 80% | 79% | 89% | 89% | 79% | 80% | 87% | 78% | 66% | 75% | 80% | 85% | 74% | 71% | 75% | 74% | 77% | 80% | 78% | 88% | 85% | |
| 93.1% | 98% | 92% | 92% | 92% | 78% | 96% | 95% | 90% | 83% | 95% | 96% | 93% | 99% | 97% | 97% | 95% | 86% | 96% | 92% | 95% | 98% |