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 Korea South. 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 | 15th 77.3% | 6th 80.7% | 11th 78.3% | 17th 77.0% | 1st 83.3% | 20th 71.3% | 6th 80.7% | 3rd 82.0% | 2nd 82.3% | 19th 72.0% | 12th 78.0% | 16th 77.0% | 10th 78.3% | 12th 78.0% | 12th 78.0% | 21st 70.0% | 6th 80.7% | 18th 73.3% | 9th 80.3% | 3rd 82.0% | 5th 81.0% | |
| 81.3% | 70% | 75% | 87% | 83% | 77% | 73% | 87% | 87% | 83% | 87% | 78% | 78% | 87% | 77% | 83% | 81% | 82% | 68% | 87% | 87% | 91% | |
| 73.9% | 79% | 79% | 78% | 78% | 95% | 71% | 67% | 67% | 77% | 67% | 71% | 74% | 63% | 71% | 78% | 70% | 75% | 67% | 78% | 75% | 71% | |
| 79.3% | 83% | 88% | 70% | 70% | 78% | 70% | 88% | 92% | 87% | 62% | 85% | 79% | 85% | 86% | 73% | 59% | 85% | 85% | 76% | 84% |