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 GD2 (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 | 13th 76.3% | 9th 79.7% | 19th 73.0% | 2nd 82.3% | 17th 75.3% | 21st 65.3% | 16th 76.0% | 14th 76.0% | 12th 78.3% | 4th 80.7% | 3rd 81.0% | 20th 67.0% | 8th 79.7% | 6th 80.0% | 11th 78.7% | 1st 83.3% | 17th 75.3% | 14th 76.0% | 10th 79.3% | 6th 80.0% | 4th 80.7% | |
| 87.7% | 72% | 94% | 73% | 90% | 87% | 76% | 90% | 84% | 91% | 96% | 94% | 79% | 94% | 95% | 79% | 99% | 89% | 89% | 93% | 89% | 89% | |
| 81.4% | 85% | 86% | 84% | 89% | 84% | 77% | 81% | 80% | 81% | 83% | 83% | 66% | 78% | 83% | 89% | 84% | 82% | 71% | 86% | 84% | 74% | |
| 62.9% | 72% | 59% | 62% | 68% | 55% | 43% | 57% | 64% | 63% | 63% | 66% | 56% | 67% | 62% | 68% | 67% | 55% | 68% | 59% | 67% | 79% |