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 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 | 14th 76.3% | 5th 81.0% | 2nd 82.0% | 4th 81.3% | 1st 82.3% | 21st 67.7% | 18th 72.7% | 15th 75.7% | 6th 80.7% | 7th 80.3% | 17th 74.7% | 8th 80.0% | 11th 77.7% | 9th 79.3% | 3rd 81.7% | 10th 79.0% | 16th 75.3% | 20th 70.3% | 12th 77.3% | 19th 72.0% | 13th 76.7% | |
| 83.5% | 79% | 86% | 84% | 84% | 84% | 78% | 79% | 88% | 88% | 83% | 84% | 81% | 83% | 94% | 84% | 83% | 87% | 86% | 81% | 79% | 78% | |
| 59.1% | 60% | 62% | 72% | 72% | 74% | 45% | 55% | 50% | 58% | 67% | 53% | 65% | 59% | 53% | 67% | 69% | 51% | 34% | 63% | 52% | 60% | |
| 89.4% | 90% | 95% | 90% | 88% | 89% | 80% | 84% | 89% | 96% | 91% | 87% | 94% | 91% | 91% | 94% | 85% | 88% | 91% | 88% | 85% | 92% |