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% | 8th 90.8% | 12th 88.5% | 3rd 92.5% | 10th 90.0% | 21st 80.3% | 14th 87.8% | 20th 81.5% | 18th 85.5% | 6th 91.8% | 5th 92.3% | 19th 83.0% | 2nd 93.5% | 17th 87.3% | 3rd 92.5% | 10th 90.0% | 15th 87.5% | 6th 91.8% | 8th 90.8% | 15th 87.5% | 13th 88.0% | |
| 88.6% | 99% | 90% | 87% | 91% | 94% | 63% | 82% | 87% | 79% | 93% | 97% | 71% | 92% | 95% | 93% | 90% | 90% | 96% | 89% | 96% | 87% | |
| 89.7% | 96% | 92% | 91% | 91% | 88% | 87% | 90% | 81% | 83% | 89% | 93% | 87% | 97% | 84% | 92% | 91% | 88% | 97% | 90% | 87% | 90% | |
| 85.3% | 91% | 90% | 89% | 91% | 88% | 86% | 86% | 77% | 83% | 88% | 83% | 78% | 87% | 83% | 87% | 82% | 83% | 83% | 93% | 83% | 81% | |
| 91.8% | 89% | 91% | 87% | 97% | 90% | 85% | 93% | 81% | 97% | 97% | 96% | 96% | 98% | 87% | 98% | 97% | 89% | 91% | 91% | 84% | 94% |