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 | 5th 92.0% | 6th 91.8% | 11th 89.5% | 3rd 92.5% | 7th 91.0% | 21st 80.8% | 18th 83.3% | 19th 83.0% | 17th 85.8% | 7th 91.0% | 4th 92.2% | 20th 81.5% | 1st 94.0% | 15th 86.3% | 2nd 93.0% | 10th 90.5% | 16th 85.8% | 11th 89.5% | 7th 91.0% | 13th 89.3% | 14th 88.3% | |
| 88.3% | 98% | 98% | 87% | 91% | 94% | 63% | 73% | 89% | 81% | 88% | 97% | 72% | 92% | 95% | 93% | 90% | 92% | 87% | 90% | 96% | 89% | |
| 89.3% | 95% | 89% | 91% | 91% | 88% | 86% | 87% | 80% | 82% | 91% | 89% | 85% | 97% | 83% | 97% | 92% | 88% | 97% | 91% | 87% | 90% | |
| 84.4% | 88% | 89% | 89% | 91% | 89% | 86% | 82% | 77% | 83% | 87% | 86% | 78% | 88% | 81% | 83% | 83% | 76% | 83% | 90% | 83% | 80% | |
| 92.6% | 87% | 91% | 91% | 97% | 93% | 88% | 91% | 86% | 97% | 98% | 97% | 91% | 99% | 86% | 99% | 97% | 87% | 91% | 93% | 91% | 94% |