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 | 7th 83.0% | 1st 87.5% | 17th 78.0% | 8th 82.8% | 20th 74.5% | 12th 80.0% | 19th 77.0% | 18th 77.5% | 15th 79.0% | 13th 80.0% | 2nd 85.8% | 21st 64.5% | 14th 79.8% | 11th 81.0% | 4th 85.2% | 6th 83.0% | 10th 82.0% | 9th 82.5% | 5th 84.0% | 16th 78.5% | 3rd 85.3% | |
| 87.9% | 94% | 99% | 82% | 89% | 86% | 77% | 81% | 99% | 92% | 79% | 96% | 61% | 94% | 96% | 92% | 92% | 90% | 90% | 97% | 84% | 75% | |
| 87.2% | 88% | 98% | 78% | 88% | 78% | 91% | 91% | 78% | 76% | 88% | 98% | 69% | 93% | 87% | 90% | 91% | 98% | 96% | 93% | 81% | 81% | |
| 67.8% | 68% | 74% | 74% | 73% | 67% | 74% | 62% | 60% | 67% | 71% | 68% | 51% | 58% | 67% | 77% | 69% | 66% | 67% | 72% | 72% | ||
| 78.3% | 82% | 79% | 78% | 81% | 67% | 78% | 74% | 73% | 81% | 82% | 81% | 77% | 74% | 74% | 82% | 80% | 74% | 77% | 74% | 77% | 100% |