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 | 1st 93.3% | 8th 91.0% | 11th 89.5% | 3rd 92.5% | 12th 88.5% | 21st 79.3% | 13th 87.5% | 19th 83.5% | 17th 84.5% | 5th 92.0% | 7th 91.5% | 20th 83.3% | 5th 92.0% | 16th 86.3% | 2nd 92.8% | 4th 92.3% | 15th 86.3% | 17th 84.5% | 8th 91.0% | 10th 91.0% | 13th 87.5% | |
| 87.9% | 95% | 90% | 87% | 91% | 94% | 60% | 81% | 90% | 75% | 91% | 96% | 72% | 90% | 92% | 95% | 92% | 90% | 89% | 90% | 96% | 89% | |
| 88.9% | 94% | 94% | 91% | 91% | 82% | 86% | 90% | 80% | 83% | 91% | 88% | 88% | 97% | 85% | 90% | 91% | 87% | 82% | 90% | 97% | 90% | |
| 85.4% | 91% | 89% | 89% | 91% | 87% | 86% | 86% | 78% | 83% | 88% | 86% | 80% | 83% | 82% | 88% | 88% | 77% | 83% | 91% | 87% | 80% | |
| 92.1% | 93% | 91% | 91% | 97% | 91% | 85% | 93% | 86% | 97% | 98% | 96% | 93% | 98% | 86% | 98% | 98% | 91% | 84% | 93% | 84% | 91% |