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 China. 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 | 6th 83.8% | 4th 85.0% | 5th 84.3% | 3rd 86.3% | 9th 81.2% | 21st 69.0% | 7th 83.0% | 12th 79.0% | 13th 78.5% | 2nd 86.8% | 10th 80.8% | 20th 70.3% | 15th 77.5% | 11th 80.3% | 1st 87.0% | 8th 81.8% | 18th 74.0% | 17th 74.3% | 14th 78.3% | 16th 75.5% | 19th 72.0% | |
| 84.1% | 89% | 87% | 87% | 87% | 79% | 61% | 86% | 89% | 85% | 94% | 86% | 77% | 88% | 86% | 87% | 89% | 85% | 85% | 74% | 79% | 86% | |
| 80.8% | 87% | 84% | 84% | 85% | 86% | 82% | 82% | 71% | 79% | 85% | 84% | 78% | 79% | 83% | 85% | 77% | 77% | 83% | 78% | 72% | 76% | |
| 69.0% | 77% | 82% | 81% | 88% | 74% | 54% | 77% | 69% | 63% | 80% | 65% | 44% | 63% | 65% | 87% | 75% | 59% | 41% | 77% | 73% | 54% | |
| 83.9% | 82% | 87% | 85% | 85% | 86% | 79% | 87% | 87% | 87% | 88% | 88% | 82% | 80% | 87% | 89% | 86% | 75% | 88% | 84% | 78% | 72% |