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 | 12th 78.0% | 7th 80.7% | 14th 77.0% | 14th 77.0% | 2nd 82.3% | 21st 71.7% | 7th 80.7% | 3rd 82.0% | 1st 84.0% | 19th 74.0% | 16th 76.7% | 18th 75.7% | 17th 76.3% | 12th 78.0% | 10th 79.3% | 3rd 82.0% | 3rd 82.0% | 11th 79.0% | 20th 73.3% | 9th 80.3% | 3rd 82.0% | |
| 81.9% | 70% | 75% | 83% | 83% | 77% | 73% | 87% | 87% | 87% | 87% | 78% | 68% | 87% | 77% | 83% | 90% | 81% | 87% | 77% | 87% | 95% | |
| 73.5% | 80% | 79% | 78% | 78% | 89% | 67% | 67% | 67% | 78% | 65% | 67% | 71% | 63% | 71% | 83% | 78% | 75% | 71% | 67% | 69% | 80% | |
| 80.7% | 84% | 88% | 70% | 70% | 81% | 75% | 88% | 92% | 87% | 70% | 85% | 88% | 79% | 86% | 72% | 78% | 90% | 79% | 76% | 85% | 71% |