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 | 6th 74.5% | 3rd 76.3% | 8th 74.0% | 6th 74.5% | 2nd 76.8% | 18th 69.8% | 15th 71.0% | 19th 69.3% | 17th 70.5% | 8th 74.0% | 4th 75.5% | 11th 73.3% | 14th 71.3% | 10th 73.5% | 5th 74.8% | 1st 77.5% | 12th 71.7% | 21st 65.8% | 13th 71.5% | 20th 68.3% | 16th 70.8% | |
| 83.4% | 85% | 87% | 78% | 77% | 80% | 77% | 85% | 91% | 84% | 85% | 86% | 83% | 83% | 89% | 88% | 89% | 88% | 75% | 81% | 77% | 84% | |
| 65.1% | 71% | 67% | 66% | 66% | 75% | 64% | 67% | 50% | 56% | 67% | 74% | 68% | 69% | 66% | 63% | 69% | 64% | 64% | 64% | 60% | 58% | |
| 54.1% | 59% | 61% | 62% | 65% | 61% | 48% | 47% | 48% | 54% | 56% | 49% | 59% | 50% | 45% | 60% | 64% | 49% | 31% | 62% | 51% | 55% | |
| 87.7% | 83% | 90% | 90% | 90% | 91% | 90% | 85% | 88% | 88% | 88% | 93% | 83% | 83% | 94% | 88% | 88% | 86% | 93% | 79% | 85% | 86% |