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 | 13th 76.5% | 1st 82.7% | 8th 78.3% | 11th 76.5% | 10th 77.8% | 14th 76.3% | 11th 76.5% | 15th 75.5% | 17th 73.8% | 8th 78.3% | 5th 79.5% | 19th 72.0% | 16th 75.5% | 3rd 80.3% | 4th 79.8% | 2nd 82.5% | 7th 78.5% | 21st 70.0% | 6th 79.3% | 18th 73.0% | 20th 71.8% | |
| 84.8% | 92% | 94% | 91% | 78% | 88% | 65% | 78% | 88% | 86% | 85% | 85% | 83% | 86% | 93% | 90% | 90% | 92% | 76% | 90% | 76% | 74% | |
| 72.8% | 71% | 80% | 72% | 78% | 62% | 87% | 75% | 61% | 61% | 75% | 78% | 69% | 75% | 73% | 75% | 78% | 75% | 75% | 74% | 67% | 67% | |
| 64.9% | 67% | 69% | 65% | 65% | 70% | 65% | 65% | 54% | 57% | 67% | 68% | 58% | 62% | 60% | 71% | 73% | 61% | 58% | 65% | 73% | 70% | |
| 85.0% | 76% | 88% | 85% | 85% | 91% | 88% | 88% | 99% | 91% | 86% | 87% | 78% | 79% | 95% | 83% | 89% | 86% | 71% | 88% | 76% | 76% |