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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 13th 76.3% | 7th 78.7% | 2nd 82.0% | 3rd 81.3% | 5th 80.3% | 20th 68.0% | 17th 72.7% | 15th 75.3% | 11th 77.0% | 6th 80.0% | 8th 78.0% | 9th 77.7% | 12th 76.7% | 9th 77.7% | 1st 84.0% | 4th 80.3% | 19th 70.0% | 16th 73.3% | 14th 76.0% | 18th 71.3% | |
| 82.9% | 79% | 85% | 84% | 84% | 84% | 79% | 79% | 88% | 85% | 83% | 84% | 82% | 82% | 89% | 84% | 83% | 87% | 80% | 81% | 76% | |
| 59.7% | 60% | 62% | 72% | 72% | 69% | 45% | 55% | 49% | 63% | 67% | 63% | 60% | 57% | 53% | 69% | 69% | 42% | 51% | 63% | 52% | |
| 88.0% | 90% | 89% | 90% | 88% | 88% | 80% | 84% | 89% | 83% | 90% | 87% | 91% | 91% | 91% | 99% | 89% | 81% | 89% | 84% | 86% |