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 Brazil. 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 | 13th 77.0% | 6th 79.3% | 10th 78.3% | 15th 76.5% | 2nd 82.3% | 7th 79.0% | 16th 75.0% | 21st 72.8% | 20th 73.3% | 11th 77.8% | 12th 77.3% | 18th 74.5% | 16th 75.0% | 5th 80.0% | 7th 79.0% | 1st 83.8% | 4th 80.8% | 19th 73.8% | 3rd 81.5% | 14th 76.7% | 7th 79.0% | |
| 86.0% | 89% | 87% | 91% | 78% | 88% | 75% | 78% | 86% | 84% | 86% | 85% | 83% | 90% | 98% | 92% | 90% | 88% | 72% | 94% | 87% | 86% | |
| 73.0% | 73% | 74% | 72% | 78% | 73% | 87% | 75% | 57% | 61% | 73% | 78% | 67% | 69% | 73% | 78% | 78% | 79% | 69% | 68% | 74% | 78% | |
| 65.4% | 67% | 68% | 65% | 65% | 77% | 66% | 59% | 54% | 57% | 66% | 58% | 58% | 62% | 58% | 60% | 74% | 70% | 68% | 76% | 70% | 76% | |
| 86.4% | 79% | 88% | 85% | 85% | 91% | 88% | 88% | 94% | 91% | 86% | 88% | 90% | 79% | 91% | 86% | 93% | 86% | 86% | 88% | 76% | 76% |