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 | 1st 84.3% | 11th 76.7% | 17th 73.3% | 7th 79.0% | 3rd 82.3% | 18th 72.0% | 11th 76.7% | 2nd 83.3% | 14th 76.3% | 15th 75.3% | 6th 80.0% | 20th 71.7% | 10th 77.3% | 4th 80.3% | 5th 80.0% | 16th 75.0% | 21st 70.3% | 18th 72.0% | 8th 78.0% | 11th 76.7% | 8th 78.0% | |
| 81.3% | 92% | 77% | 72% | 83% | 92% | 70% | 86% | 97% | 83% | 92% | 83% | 83% | 83% | 77% | 85% | 77% | 78% | 68% | 77% | 84% | 69% | |
| 71.1% | 75% | 77% | 78% | 75% | 81% | 75% | 71% | 69% | 69% | 65% | 72% | 59% | 67% | 70% | 77% | 72% | 51% | 69% | 78% | 67% | 77% | |
| 78.8% | 86% | 76% | 70% | 79% | 74% | 71% | 73% | 84% | 77% | 69% | 85% | 73% | 82% | 94% | 78% | 76% | 82% | 79% | 79% | 79% | 88% |