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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 5th 83.3% | 4th 83.7% | 17th 78.7% | 9th 82.3% | 20th 75.3% | 19th 77.3% | 16th 78.7% | 21st 74.7% | 17th 78.7% | 14th 79.3% | 6th 83.0% | 11th 80.7% | 15th 79.0% | 6th 83.0% | 3rd 84.3% | 2nd 84.7% | 10th 81.3% | 13th 80.0% | 6th 83.0% | 1st 86.3% | 12th 80.3% | |
| 93.3% | 98% | 98% | 92% | 96% | 82% | 96% | 98% | 81% | 91% | 98% | 95% | 94% | 95% | 94% | 96% | 98% | 82% | 92% | 94% | 96% | 94% | |
| 68.3% | 69% | 74% | 77% | 68% | 69% | 69% | 62% | 57% | 70% | 69% | 68% | 62% | 61% | 65% | 73% | 72% | 72% | 67% | 70% | 72% | 69% | |
| 80.9% | 83% | 79% | 67% | 83% | 75% | 67% | 76% | 86% | 75% | 71% | 86% | 86% | 81% | 90% | 84% | 84% | 90% | 81% | 85% | 91% | 78% |