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 Canada. 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 | 3rd 85.5% | 10th 84.0% | 18th 80.8% | 7th 84.3% | 12th 83.0% | 21st 74.5% | 11th 83.8% | 15th 82.3% | 14th 82.5% | 7th 84.3% | 6th 84.8% | 15th 82.3% | 7th 84.3% | 2nd 85.8% | 1st 90.3% | 5th 85.0% | 19th 80.2% | 20th 80.0% | 3rd 85.5% | 12th 83.0% | 17th 81.0% | |
| 85.4% | 86% | 86% | 74% | 78% | 79% | 71% | 82% | 90% | 86% | 78% | 92% | 88% | 90% | 96% | 98% | 90% | 88% | 83% | 89% | 88% | 82% | |
| 85.5% | 90% | 84% | 86% | 91% | 87% | 80% | 84% | 88% | 85% | 90% | 81% | 84% | 89% | 90% | 91% | 84% | 77% | 79% | 88% | 82% | 85% | |
| 74.2% | 78% | 77% | 79% | 80% | 84% | 66% | 78% | 65% | 67% | 77% | 75% | 74% | 66% | 68% | 78% | 78% | 70% | 73% | 77% | 77% | 72% | |
| 87.6% | 88% | 89% | 84% | 88% | 82% | 81% | 91% | 86% | 92% | 92% | 91% | 83% | 92% | 89% | 94% | 88% | 86% | 85% | 88% | 85% | 85% |