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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 79.5% | 1st 82.0% | 7th 76.5% | 4th 79.0% | 8th 76.3% | 15th 71.5% | 11th 75.0% | 19th 68.0% | 6th 77.5% | 21st 64.8% | 5th 78.3% | 20th 67.5% | 13th 72.2% | 1st 82.0% | 18th 69.0% | 16th 70.5% | 9th 76.0% | 17th 70.5% | 10th 75.3% | 12th 73.3% | 14th 72.0% | |
| 86.2% | 92% | 96% | 82% | 86% | 80% | 77% | 89% | 93% | 93% | 75% | 94% | 83% | 90% | 98% | 70% | 67% | 92% | 89% | 86% | 86% | 93% | |
| 79.8% | 78% | 87% | 88% | 88% | 82% | 79% | 87% | 57% | 80% | 68% | 84% | 69% | 82% | 87% | 72% | 79% | 83% | 89% | 85% | 78% | 74% | |
| 58.4% | 68% | 68% | 68% | 68% | 66% | 51% | 51% | 54% | 63% | 48% | 54% | 51% | 50% | 62% | 68% | 62% | 62% | 37% | 63% | 55% | 58% | |
| 72.0% | 80% | 77% | 68% | 74% | 77% | 79% | 73% | 68% | 74% | 68% | 81% | 67% | 67% | 81% | 66% | 74% | 67% | 67% | 67% | 74% | 63% |