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 | 4th 79.0% | 2nd 81.0% | 9th 76.0% | 8th 76.3% | 3rd 79.3% | 20th 65.7% | 14th 72.3% | 12th 75.3% | 13th 72.7% | 11th 75.7% | 6th 77.3% | 9th 76.0% | 17th 71.0% | 16th 71.7% | 1st 81.3% | 5th 78.3% | 19th 68.0% | 15th 72.0% | 7th 77.0% | 20th 65.7% | 18th 69.7% | |
| 88.2% | 96% | 96% | 96% | 94% | 96% | 83% | 80% | 96% | 88% | 88% | 97% | 81% | 77% | 87% | 93% | 92% | 88% | 88% | 88% | 72% | 77% | |
| 58.0% | 61% | 64% | 63% | 68% | 66% | 51% | 59% | 46% | 55% | 57% | 53% | 61% | 58% | 48% | 68% | 62% | 52% | 48% | 63% | 54% | 61% | |
| 76.8% | 80% | 83% | 69% | 67% | 76% | 63% | 78% | 84% | 75% | 82% | 82% | 86% | 78% | 80% | 83% | 81% | 64% | 80% | 80% | 71% | 71% |