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 | 2nd 86.0% | 1st 88.0% | 19th 76.3% | 8th 82.8% | 21st 74.5% | 10th 80.0% | 17th 77.5% | 20th 74.5% | 14th 78.5% | 18th 76.5% | 3rd 85.3% | 16th 77.8% | 15th 78.3% | 9th 81.8% | 3rd 85.3% | 6th 84.3% | 12th 79.0% | 13th 79.0% | 5th 84.5% | 6th 84.3% | 11th 80.0% | |
| 87.9% | 100% | 99% | 75% | 89% | 83% | 77% | 81% | 92% | 90% | 75% | 94% | 90% | 92% | 96% | 94% | 93% | 84% | 85% | 97% | 84% | 75% | |
| 86.6% | 88% | 98% | 78% | 88% | 72% | 91% | 93% | 78% | 76% | 82% | 98% | 93% | 81% | 87% | 93% | 91% | 92% | 84% | 93% | 81% | 81% | |
| 69.0% | 74% | 74% | 74% | 73% | 72% | 74% | 62% | 60% | 67% | 68% | 68% | 51% | 58% | 67% | 73% | 72% | 63% | 70% | 74% | 72% | 82% | |
| 79.2% | 82% | 81% | 78% | 81% | 71% | 78% | 74% | 68% | 81% | 81% | 81% | 77% | 82% | 77% | 81% | 81% | 77% | 77% | 74% | 100% | 82% |