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 | 8th 81.8% | 1st 88.0% | 18th 76.3% | 6th 82.8% | 20th 73.8% | 12th 80.0% | 15th 77.0% | 15th 77.0% | 15th 77.0% | 13th 79.3% | 1st 88.0% | 21st 67.8% | 18th 76.3% | 8th 81.8% | 4th 85.3% | 11th 81.0% | 6th 82.8% | 14th 78.7% | 3rd 86.3% | 8th 81.8% | 5th 83.7% | |
| 88.1% | 89% | 99% | 75% | 89% | 81% | 77% | 81% | 92% | 90% | 79% | 98% | 84% | 94% | 96% | 97% | 81% | 98% | 86% | 97% | 84% | 84% | |
| 86.0% | 82% | 98% | 78% | 88% | 78% | 91% | 91% | 78% | 76% | 88% | 98% | 64% | 81% | 87% | 88% | 95% | 96% | 94% | 93% | 81% | 81% | |
| 67.9% | 74% | 74% | 74% | 73% | 65% | 74% | 62% | 60% | 61% | 68% | 74% | 51% | 56% | 67% | 72% | 68% | 69% | 63% | 74% | 77% | 70% | |
| 79.1% | 82% | 81% | 78% | 81% | 71% | 78% | 74% | 78% | 81% | 82% | 82% | 72% | 74% | 77% | 84% | 80% | 68% | 72% | 81% | 85% | 100% |