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 GD1 (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 | 8th 76.3% | 1st 80.8% | 7th 77.5% | 9th 76.0% | 14th 71.5% | 16th 70.0% | 6th 77.8% | 19th 68.0% | 5th 77.8% | 21st 65.5% | 3rd 78.3% | 20th 67.5% | 12th 74.0% | 2nd 79.3% | 18th 69.0% | 13th 73.5% | 10th 75.8% | 11th 75.0% | 4th 78.0% | 15th 70.3% | 17th 69.8% | |
| 87.0% | 92% | 96% | 86% | 86% | 82% | 83% | 89% | 93% | 96% | 73% | 94% | 83% | 94% | 98% | 70% | 75% | 92% | 89% | 80% | 89% | 87% | |
| 80.0% | 77% | 87% | 88% | 76% | 78% | 79% | 87% | 57% | 80% | 76% | 84% | 69% | 85% | 87% | 80% | 83% | 83% | 84% | 95% | 76% | 69% | |
| 57.0% | 62% | 63% | 68% | 68% | 58% | 45% | 62% | 54% | 63% | 45% | 54% | 51% | 50% | 51% | 60% | 63% | 54% | 50% | 63% | 54% | 60% | |
| 71.4% | 74% | 77% | 68% | 74% | 68% | 73% | 73% | 68% | 72% | 68% | 81% | 67% | 67% | 81% | 66% | 73% | 74% | 77% | 74% | 62% | 63% |