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 | 13th 76.0% | 1st 82.5% | 6th 78.3% | 10th 77.3% | 15th 75.8% | 17th 74.8% | 16th 75.0% | 7th 77.8% | 19th 74.5% | 8th 77.5% | 3rd 79.8% | 21st 68.8% | 8th 77.5% | 2nd 80.3% | 5th 78.8% | 4th 79.3% | 11th 77.3% | 17th 74.8% | 12th 76.5% | 20th 73.0% | 13th 76.0% | |
| 84.3% | 91% | 94% | 91% | 81% | 79% | 65% | 78% | 90% | 83% | 86% | 95% | 61% | 84% | 98% | 93% | 89% | 85% | 89% | 85% | 67% | 87% | |
| 72.9% | 71% | 80% | 72% | 78% | 66% | 80% | 75% | 67% | 61% | 72% | 78% | 65% | 78% | 73% | 68% | 76% | 75% | 71% | 68% | 78% | 78% | |
| 63.1% | 63% | 68% | 65% | 65% | 70% | 66% | 59% | 59% | 57% | 66% | 58% | 61% | 66% | 59% | 69% | 67% | 61% | 58% | 65% | 61% | 63% | |
| 86.5% | 79% | 88% | 85% | 85% | 88% | 88% | 88% | 95% | 97% | 86% | 88% | 88% | 82% | 91% | 85% | 85% | 88% | 81% | 88% | 86% | 76% |