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 | 17th 68.7% | 6th 74.0% | 11th 71.3% | 9th 72.3% | 6th 74.0% | 21st 63.0% | 11th 71.3% | 8th 73.0% | 11th 71.3% | 1st 77.3% | 16th 70.3% | 18th 68.3% | 14th 70.7% | 4th 74.3% | 2nd 77.0% | 3rd 75.7% | 19th 67.7% | 10th 72.0% | 14th 70.7% | 20th 64.3% | 4th 74.3% | |
| 78.4% | 63% | 76% | 73% | 71% | 77% | 79% | 83% | 85% | 82% | 85% | 77% | 81% | 81% | 85% | 82% | 80% | 76% | 78% | 79% | 68% | 86% | |
| 73.9% | 79% | 78% | 79% | 84% | 83% | 66% | 67% | 68% | 70% | 76% | 71% | 66% | 70% | 75% | 82% | 80% | 66% | 73% | 73% | 72% | 73% | |
| 62.2% | 64% | 68% | 62% | 62% | 62% | 44% | 64% | 66% | 62% | 71% | 63% | 58% | 61% | 63% | 67% | 67% | 61% | 65% | 60% | 53% | 64% |