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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 11th 78.7% | 5th 80.3% | 18th 73.0% | 2nd 82.3% | 17th 73.7% | 20th 65.3% | 15th 75.7% | 16th 74.7% | 3rd 82.0% | 8th 79.3% | 1st 83.0% | 19th 68.0% | 8th 79.3% | 7th 79.7% | 13th 76.3% | 4th 81.0% | 10th 79.0% | 21st 61.7% | 6th 80.0% | 14th 76.0% | 12th 77.0% | |
| 87.5% | 82% | 94% | 73% | 90% | 87% | 76% | 90% | 84% | 96% | 96% | 94% | 90% | 95% | 96% | 79% | 93% | 90% | 71% | 93% | 89% | 79% | |
| 80.4% | 85% | 86% | 84% | 89% | 83% | 77% | 81% | 78% | 87% | 83% | 83% | 66% | 78% | 81% | 81% | 84% | 76% | 67% | 85% | 76% | 78% | |
| 61.6% | 69% | 61% | 62% | 68% | 51% | 43% | 56% | 62% | 63% | 59% | 72% | 48% | 65% | 62% | 69% | 66% | 71% | 47% | 62% | 63% | 74% |