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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 13th 80.5% | 1st 88.0% | 18th 76.8% | 8th 82.0% | 19th 75.8% | 12th 80.5% | 17th 77.0% | 20th 75.5% | 16th 77.5% | 14th 79.3% | 2nd 86.3% | 21st 74.8% | 15th 78.8% | 9th 81.8% | 4th 85.2% | 5th 85.0% | 11th 81.0% | 10th 81.2% | 3rd 85.8% | 7th 82.7% | 6th 83.7% | |
| 87.5% | 89% | 99% | 73% | 86% | 83% | 79% | 81% | 92% | 92% | 79% | 98% | 84% | 94% | 96% | 88% | 91% | 84% | 84% | 97% | 84% | 84% | |
| 88.8% | 77% | 98% | 82% | 88% | 88% | 91% | 91% | 78% | 76% | 88% | 98% | 93% | 91% | 87% | 98% | 96% | 92% | 94% | 91% | 86% | 81% | |
| 68.0% | 74% | 74% | 74% | 73% | 66% | 74% | 62% | 60% | 61% | 68% | 68% | 50% | 56% | 67% | 74% | 72% | 71% | 63% | 74% | 77% | 70% | |
| 79.4% | 82% | 81% | 78% | 81% | 66% | 78% | 74% | 72% | 81% | 82% | 81% | 72% | 74% | 77% | 81% | 81% | 77% | 84% | 81% | 84% | 100% |