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 | 4th 92.3% | 9th 89.8% | 11th 89.5% | 3rd 92.5% | 11th 89.5% | 20th 80.8% | 17th 85.0% | 19th 84.3% | 18th 84.5% | 6th 91.8% | 5th 92.0% | 21st 76.5% | 1st 93.5% | 16th 85.5% | 2nd 93.0% | 10th 89.8% | 15th 88.3% | 8th 90.5% | 13th 89.0% | 7th 91.0% | 14th 88.8% | |
| 87.7% | 97% | 90% | 87% | 91% | 94% | 63% | 81% | 87% | 81% | 90% | 94% | 67% | 90% | 92% | 93% | 92% | 96% | 92% | 88% | 87% | 89% | |
| 89.6% | 94% | 89% | 91% | 91% | 88% | 86% | 85% | 85% | 77% | 91% | 91% | 88% | 97% | 84% | 95% | 88% | 88% | 91% | 89% | 97% | 97% | |
| 84.8% | 89% | 89% | 89% | 91% | 89% | 86% | 84% | 78% | 83% | 89% | 86% | 65% | 88% | 79% | 88% | 84% | 79% | 82% | 89% | 89% | 85% | |
| 91.7% | 89% | 91% | 91% | 97% | 87% | 88% | 90% | 87% | 97% | 97% | 97% | 86% | 99% | 87% | 96% | 95% | 90% | 97% | 90% | 91% | 84% |