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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 82.3% | 4th 81.0% | 13th 76.5% | 12th 76.5% | 9th 77.8% | 15th 74.8% | 14th 75.0% | 20th 72.5% | 19th 72.8% | 10th 77.0% | 1st 82.5% | 17th 73.5% | 11th 76.8% | 8th 78.3% | 1st 82.5% | 5th 80.0% | 6th 79.0% | 16th 74.0% | 7th 78.5% | 18th 73.3% | 21st 69.5% | |
| 85.5% | 94% | 94% | 91% | 78% | 88% | 65% | 78% | 88% | 86% | 86% | 95% | 78% | 94% | 95% | 93% | 91% | 88% | 81% | 87% | 79% | 67% | |
| 71.9% | 76% | 74% | 72% | 78% | 69% | 80% | 75% | 57% | 57% | 75% | 81% | 67% | 69% | 65% | 78% | 70% | 78% | 78% | 74% | 69% | 67% | |
| 63.5% | 65% | 68% | 65% | 65% | 63% | 66% | 59% | 53% | 57% | 66% | 68% | 58% | 65% | 58% | 73% | 74% | 59% | 55% | 65% | 64% | 68% | |
| 86.5% | 94% | 88% | 78% | 85% | 91% | 88% | 88% | 92% | 91% | 81% | 86% | 91% | 79% | 95% | 86% | 85% | 91% | 82% | 88% | 81% | 76% |