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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 75.0% | 12th 71.5% | 11th 72.0% | 6th 74.8% | 18th 67.0% | 20th 64.5% | 3rd 75.0% | 13th 70.7% | 16th 69.2% | 10th 73.5% | 1st 76.3% | 8th 74.0% | 14th 70.5% | 3rd 75.0% | 9th 73.8% | 7th 74.3% | 18th 67.0% | 21st 62.7% | 2nd 75.3% | 17th 68.5% | 15th 69.8% | |
| 67.3% | 64% | 65% | 65% | 60% | 65% | 54% | 66% | 68% | 69% | 74% | 76% | 77% | 74% | 77% | 70% | 67% | 67% | 57% | 64% | 65% | 69% | |
| 74.4% | 84% | 73% | 77% | 84% | 69% | 69% | 77% | 72% | 67% | 76% | 77% | 77% | 78% | 67% | 76% | 72% | 71% | 72% | 77% | 76% | 71% | |
| 63.6% | 72% | 68% | 72% | 73% | 63% | 56% | 65% | 59% | 59% | 60% | 68% | 58% | 59% | 65% | 67% | 68% | 55% | 51% | 68% | 62% | 68% | |
| 80.5% | 80% | 80% | 74% | 82% | 71% | 79% | 92% | 84% | 82% | 84% | 84% | 84% | 71% | 91% | 82% | 90% | 75% | 71% | 92% | 71% | 71% |