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 77.0% | 4th 80.0% | 2nd 82.0% | 2nd 82.0% | 7th 79.0% | 21st 69.3% | 19th 72.7% | 10th 77.7% | 16th 76.0% | 13th 77.3% | 10th 77.7% | 5th 79.3% | 8th 78.0% | 5th 79.3% | 1st 82.3% | 8th 78.0% | 15th 76.7% | 17th 75.3% | 18th 75.0% | 20th 71.3% | 12th 77.3% | |
| 83.0% | 79% | 86% | 84% | 84% | 84% | 83% | 79% | 84% | 85% | 83% | 84% | 82% | 81% | 94% | 85% | 86% | 81% | 87% | 81% | 76% | 75% | |
| 60.2% | 62% | 62% | 72% | 72% | 64% | 45% | 55% | 60% | 55% | 59% | 63% | 65% | 58% | 53% | 72% | 64% | 61% | 51% | 60% | 52% | 60% | |
| 88.7% | 90% | 92% | 90% | 90% | 89% | 80% | 84% | 89% | 88% | 90% | 86% | 91% | 95% | 91% | 90% | 84% | 88% | 88% | 84% | 86% | 97% |