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 Mexico. 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 | 8th 72.5% | 12th 71.5% | 11th 72.0% | 5th 74.8% | 1st 76.5% | 19th 65.3% | 1st 76.5% | 8th 72.5% | 17th 69.2% | 16th 69.3% | 4th 75.5% | 21st 64.3% | 13th 70.8% | 8th 72.5% | 3rd 76.3% | 6th 73.5% | 18th 67.5% | 15th 69.8% | 13th 70.8% | 19th 65.3% | 6th 73.5% | |
| 67.7% | 67% | 65% | 65% | 60% | 67% | 57% | 66% | 69% | 69% | 70% | 73% | 76% | 77% | 77% | 73% | 69% | 60% | 62% | 64% | 60% | 76% | |
| 73.4% | 82% | 73% | 77% | 84% | 77% | 69% | 80% | 72% | 65% | 76% | 77% | 51% | 78% | 67% | 78% | 73% | 72% | 71% | 77% | 67% | 76% | |
| 64.7% | 72% | 68% | 72% | 73% | 71% | 56% | 68% | 59% | 59% | 60% | 68% | 46% | 57% | 65% | 72% | 68% | 54% | 65% | 71% | 63% | 71% | |
| 79.8% | 69% | 80% | 74% | 82% | 91% | 79% | 92% | 90% | 84% | 71% | 84% | 84% | 71% | 81% | 82% | 84% | 84% | 81% | 71% | 71% | 71% |