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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 7th 79.7% | 6th 80.7% | 9th 78.3% | 14th 77.0% | 1st 87.0% | 20th 70.0% | 4th 82.0% | 3rd 82.3% | 2nd 82.7% | 15th 76.3% | 10th 78.0% | 13th 77.3% | 8th 79.0% | 10th 78.0% | 17th 75.7% | 18th 75.0% | 4th 82.0% | 19th 74.7% | 10th 78.0% | 15th 76.3% | |
| 81.5% | 72% | 75% | 87% | 83% | 90% | 73% | 87% | 88% | 83% | 87% | 78% | 81% | 87% | 77% | 80% | 83% | 81% | 77% | 77% | 83% | |
| 74.5% | 80% | 79% | 78% | 78% | 95% | 67% | 75% | 67% | 78% | 72% | 71% | 72% | 65% | 71% | 80% | 75% | 75% | 62% | 78% | 71% | |
| 79.6% | 87% | 88% | 70% | 70% | 76% | 70% | 84% | 92% | 87% | 70% | 85% | 79% | 85% | 86% | 67% | 67% | 90% | 85% | 79% | 75% |