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 GD2 (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 | 15th 79.3% | 4th 83.3% | 11th 81.0% | 7th 82.3% | 20th 74.7% | 19th 75.7% | 18th 76.0% | 21st 74.7% | 17th 79.0% | 14th 79.7% | 6th 83.0% | 12th 80.7% | 10th 81.0% | 7th 82.3% | 1st 85.7% | 2nd 84.3% | 5th 83.0% | 12th 80.7% | 2nd 84.3% | 15th 79.3% | 9th 81.3% | |
| 92.5% | 95% | 97% | 92% | 96% | 82% | 92% | 98% | 81% | 92% | 92% | 95% | 95% | 98% | 92% | 98% | 98% | 95% | 92% | 98% | 82% | 82% | |
| 68.6% | 66% | 74% | 77% | 68% | 66% | 69% | 62% | 57% | 66% | 72% | 68% | 61% | 62% | 65% | 73% | 72% | 73% | 66% | 70% | 72% | 82% | |
| 80.5% | 77% | 79% | 74% | 83% | 76% | 66% | 68% | 86% | 79% | 75% | 86% | 86% | 83% | 90% | 86% | 83% | 81% | 84% | 85% | 84% | 80% |