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 | 11th 73.3% | 2nd 77.5% | 9th 74.0% | 8th 74.5% | 1st 77.8% | 21st 66.5% | 13th 72.0% | 19th 69.0% | 15th 70.3% | 5th 75.0% | 7th 74.8% | 6th 74.8% | 14th 71.3% | 15th 70.3% | 4th 75.8% | 3rd 77.0% | 18th 69.3% | 17th 69.8% | 12th 72.8% | 20th 67.0% | 10th 74.0% | |
| 83.1% | 85% | 91% | 78% | 77% | 85% | 76% | 89% | 88% | 84% | 86% | 88% | 89% | 82% | 89% | 88% | 87% | 71% | 74% | 78% | 77% | 83% | |
| 65.0% | 68% | 68% | 66% | 66% | 69% | 64% | 67% | 51% | 56% | 67% | 69% | 68% | 70% | 62% | 66% | 69% | 64% | 65% | 66% | 58% | ||
| 56.7% | 59% | 61% | 62% | 65% | 70% | 45% | 47% | 49% | 53% | 56% | 49% | 59% | 50% | 45% | 63% | 69% | 61% | 49% | 62% | 56% | 61% | |
| 85.5% | 81% | 90% | 90% | 90% | 87% | 81% | 85% | 88% | 88% | 91% | 93% | 83% | 83% | 85% | 86% | 83% | 81% | 91% | 85% | 77% | 78% |