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 | 7th 77.8% | 2nd 80.8% | 12th 76.5% | 9th 77.3% | 8th 77.5% | 16th 74.5% | 15th 75.0% | 14th 76.0% | 19th 73.0% | 3rd 79.8% | 13th 76.3% | 21st 69.5% | 6th 78.5% | 5th 79.5% | 3rd 79.8% | 1st 81.5% | 10th 77.3% | 18th 73.0% | 11th 76.5% | 20th 72.5% | 17th 74.5% | |
| 84.0% | 94% | 87% | 91% | 81% | 88% | 65% | 78% | 90% | 84% | 93% | 85% | 58% | 92% | 94% | 92% | 90% | 85% | 83% | 87% | 74% | 74% | |
| 72.8% | 71% | 80% | 72% | 78% | 65% | 78% | 75% | 62% | 61% | 73% | 76% | 69% | 72% | 73% | 82% | 74% | 76% | 75% | 68% | 69% | 79% | |
| 64.4% | 67% | 68% | 65% | 65% | 70% | 67% | 59% | 57% | 56% | 67% | 58% | 59% | 68% | 60% | 68% | 75% | 62% | 53% | 70% | 70% | 69% | |
| 84.8% | 79% | 88% | 78% | 85% | 87% | 88% | 88% | 95% | 91% | 86% | 86% | 92% | 82% | 91% | 77% | 87% | 86% | 81% | 81% | 77% | 76% |