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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 84.0% | 13th 77.0% | 19th 75.0% | 10th 78.0% | 2nd 83.7% | 21st 72.0% | 13th 77.0% | 3rd 83.0% | 16th 76.3% | 16th 76.3% | 10th 78.0% | 18th 76.0% | 12th 77.7% | 5th 81.0% | 20th 74.3% | 6th 80.3% | 3rd 83.0% | 15th 76.7% | 6th 80.3% | 6th 80.3% | 9th 78.7% | |
| 83.1% | 88% | 77% | 77% | 80% | 98% | 70% | 86% | 96% | 83% | 92% | 77% | 83% | 83% | 77% | 80% | 78% | 84% | 84% | 83% | 85% | 84% | |
| 72.6% | 78% | 75% | 78% | 75% | 80% | 75% | 72% | 69% | 69% | 65% | 72% | 72% | 67% | 70% | 69% | 76% | 75% | 61% | 78% | 71% | 77% | |
| 79.9% | 86% | 79% | 70% | 79% | 73% | 71% | 73% | 84% | 77% | 72% | 85% | 73% | 83% | 96% | 74% | 87% | 90% | 85% | 80% | 85% | 75% |