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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 9th 89.8% | 7th 90.5% | 11th 89.5% | 3rd 92.5% | 14th 88.0% | 20th 81.0% | 18th 83.5% | 19th 82.5% | 17th 84.5% | 5th 91.3% | 4th 92.0% | 21st 74.8% | 2nd 93.3% | 15th 87.0% | 1st 94.0% | 7th 90.5% | 11th 89.5% | 16th 85.8% | 6th 90.8% | 10th 89.8% | 13th 89.3% | |
| 86.9% | 93% | 98% | 87% | 91% | 85% | 63% | 73% | 87% | 83% | 90% | 94% | 65% | 92% | 95% | 96% | 90% | 95% | 76% | 90% | 92% | 90% | |
| 89.0% | 90% | 92% | 91% | 91% | 88% | 90% | 85% | 80% | 77% | 91% | 92% | 85% | 97% | 83% | 97% | 91% | 86% | 97% | 89% | 87% | 90% | |
| 84.6% | 89% | 89% | 89% | 91% | 89% | 86% | 86% | 78% | 83% | 86% | 86% | 60% | 88% | 82% | 88% | 85% | 85% | 79% | 91% | 83% | 83% | |
| 91.8% | 87% | 83% | 91% | 97% | 90% | 85% | 90% | 85% | 95% | 98% | 96% | 89% | 96% | 88% | 95% | 96% | 92% | 91% | 93% | 97% | 94% |