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 GD2 (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 80.0% | 17th 74.0% | 18th 73.3% | 14th 77.0% | 3rd 81.7% | 19th 73.0% | 6th 81.0% | 2nd 82.3% | 1st 82.7% | 15th 74.7% | 12th 77.7% | 15th 74.7% | 10th 78.3% | 7th 80.0% | 21st 71.3% | 12th 77.7% | 4th 81.3% | 20th 71.7% | 4th 81.3% | 9th 78.7% | 10th 78.3% | |
| 79.4% | 72% | 66% | 72% | 83% | 72% | 73% | 87% | 88% | 83% | 87% | 78% | 68% | 87% | 77% | 83% | 75% | 81% | 77% | 87% | 90% | 82% | |
| 73.3% | 80% | 79% | 78% | 78% | 95% | 71% | 68% | 67% | 78% | 67% | 66% | 71% | 63% | 77% | 77% | 78% | 75% | 59% | 78% | 62% | 72% | |
| 80.2% | 88% | 77% | 70% | 70% | 78% | 75% | 88% | 92% | 87% | 70% | 89% | 85% | 85% | 86% | 54% | 80% | 88% | 79% | 79% | 84% | 81% |