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 | 9th 78.7% | 13th 76.0% | 18th 75.0% | 10th 78.0% | 1st 84.0% | 21st 72.0% | 15th 76.0% | 2nd 83.3% | 12th 76.3% | 19th 74.3% | 5th 82.0% | 19th 74.3% | 11th 77.7% | 7th 81.0% | 13th 76.0% | 3rd 82.7% | 5th 82.0% | 17th 75.3% | 8th 80.3% | 4th 82.3% | 16th 75.7% | |
| 82.2% | 80% | 77% | 77% | 80% | 92% | 70% | 86% | 97% | 83% | 88% | 80% | 91% | 83% | 80% | 77% | 87% | 87% | 77% | 77% | 88% | 69% | |
| 71.4% | 77% | 72% | 78% | 75% | 81% | 75% | 69% | 69% | 69% | 69% | 72% | 59% | 67% | 69% | 77% | 77% | 69% | 65% | 78% | 65% | 68% | |
| 81.1% | 79% | 79% | 70% | 79% | 79% | 71% | 73% | 84% | 77% | 66% | 94% | 73% | 83% | 94% | 74% | 84% | 90% | 84% | 86% | 94% | 90% |