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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 15th 76.0% | 5th 79.3% | 1st 82.7% | 7th 78.3% | 11th 77.3% | 13th 76.8% | 9th 77.5% | 17th 75.0% | 18th 74.5% | 21st 72.3% | 4th 79.5% | 14th 76.5% | 2nd 81.8% | 10th 77.5% | 18th 74.5% | 15th 76.0% | 7th 78.3% | 3rd 80.3% | 20th 73.0% | 5th 79.3% | 12th 77.0% | |
| 86.0% | 89% | 87% | 94% | 91% | 79% | 65% | 87% | 78% | 90% | 84% | 89% | 84% | 95% | 83% | 83% | 87% | 88% | 88% | 88% | 90% | 86% | |
| 72.4% | 71% | 78% | 80% | 72% | 67% | 87% | 69% | 75% | 61% | 57% | 73% | 73% | 78% | 69% | 75% | 73% | 84% | 75% | 62% | 74% | 67% | |
| 65.0% | 65% | 76% | 69% | 65% | 70% | 67% | 71% | 59% | 53% | 57% | 76% | 64% | 68% | 61% | 61% | 53% | 61% | 70% | 63% | 65% | 70% | |
| 85.9% | 79% | 76% | 88% | 85% | 93% | 88% | 83% | 88% | 94% | 91% | 80% | 85% | 86% | 97% | 79% | 91% | 80% | 88% | 79% | 88% | 85% |