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 | 2nd 85.8% | 5th 85.0% | 6th 84.5% | 1st 85.8% | 8th 82.3% | 21st 68.3% | 8th 82.3% | 16th 75.5% | 14th 76.3% | 7th 83.3% | 10th 80.8% | 19th 73.0% | 13th 78.5% | 11th 79.5% | 4th 85.3% | 3rd 85.5% | 20th 72.8% | 18th 73.5% | 12th 78.8% | 14th 76.3% | 17th 74.5% | |
| 84.7% | 94% | 87% | 87% | 87% | 85% | 61% | 87% | 91% | 85% | 94% | 89% | 75% | 87% | 86% | 93% | 91% | 67% | 85% | 73% | 86% | 88% | |
| 80.8% | 90% | 84% | 85% | 85% | 83% | 79% | 84% | 64% | 71% | 87% | 84% | 78% | 84% | 82% | 88% | 86% | 77% | 77% | 84% | 77% | 68% | |
| 69.5% | 77% | 82% | 81% | 86% | 76% | 54% | 77% | 60% | 63% | 72% | 61% | 58% | 63% | 63% | 75% | 78% | 67% | 48% | 77% | 68% | 73% | |
| 82.6% | 82% | 87% | 85% | 85% | 85% | 79% | 81% | 87% | 86% | 80% | 89% | 81% | 80% | 87% | 85% | 87% | 80% | 84% | 81% | 74% | 69% |