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 | 2nd 79.5% | 1st 82.0% | 11th 76.5% | 4th 79.0% | 6th 77.3% | 16th 72.3% | 13th 73.8% | 19th 68.0% | 7th 77.0% | 21st 66.3% | 5th 78.8% | 20th 67.5% | 14th 73.3% | 3rd 79.3% | 15th 72.5% | 12th 75.3% | 10th 76.8% | 7th 77.0% | 7th 77.0% | 17th 70.5% | 17th 70.5% | |
| 87.9% | 94% | 96% | 82% | 86% | 89% | 83% | 89% | 93% | 93% | 75% | 93% | 83% | 94% | 98% | 76% | 81% | 92% | 90% | 86% | 83% | 90% | |
| 81.9% | 83% | 87% | 88% | 88% | 82% | 79% | 87% | 57% | 80% | 74% | 87% | 69% | 82% | 87% | 76% | 87% | 83% | 96% | 87% | 84% | 77% | |
| 58.0% | 62% | 68% | 68% | 68% | 68% | 54% | 51% | 54% | 61% | 48% | 54% | 51% | 50% | 51% | 65% | 63% | 62% | 45% | 67% | 57% | 52% | |
| 71.1% | 79% | 77% | 68% | 74% | 70% | 73% | 68% | 68% | 74% | 68% | 81% | 67% | 67% | 81% | 73% | 70% | 70% | 77% | 68% | 58% | 63% |