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 93.8% | 10th 90.0% | 11th 89.5% | 4th 92.5% | 14th 87.0% | 20th 80.8% | 16th 85.0% | 18th 83.0% | 17th 84.5% | 6th 91.5% | 6th 91.5% | 21st 78.3% | 3rd 93.0% | 15th 86.3% | 2nd 93.3% | 5th 92.0% | 12th 88.8% | 9th 90.5% | 8th 91.3% | 12th 88.8% | 19th 81.8% | |
| 87.8% | 99% | 90% | 87% | 91% | 90% | 63% | 78% | 87% | 81% | 93% | 96% | 71% | 92% | 95% | 94% | 93% | 85% | 89% | 89% | 91% | 89% | |
| 89.2% | 97% | 90% | 91% | 91% | 82% | 86% | 87% | 80% | 77% | 91% | 89% | 87% | 97% | 83% | 91% | 91% | 90% | 97% | 90% | 97% | 90% | |
| 84.5% | 90% | 89% | 89% | 91% | 90% | 86% | 84% | 78% | 83% | 86% | 86% | 60% | 88% | 79% | 90% | 85% | 83% | 78% | 93% | 83% | 84% | |
| 91.4% | 89% | 91% | 91% | 97% | 86% | 88% | 91% | 87% | 97% | 96% | 95% | 95% | 95% | 88% | 98% | 99% | 97% | 98% | 93% | 84% | 64% |