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 | 9th 84.0% | 9th 84.0% | 18th 80.8% | 7th 84.3% | 15th 83.0% | 21st 74.5% | 13th 83.3% | 11th 83.8% | 6th 84.8% | 3rd 86.3% | 12th 83.5% | 17th 81.0% | 2nd 87.5% | 7th 84.3% | 1st 88.5% | 4th 85.8% | 20th 78.0% | 19th 79.0% | 5th 85.5% | 16th 81.5% | 13th 83.3% | |
| 84.5% | 84% | 86% | 74% | 76% | 81% | 71% | 82% | 90% | 89% | 78% | 92% | 83% | 94% | 96% | 93% | 92% | 84% | 73% | 89% | 84% | 83% | |
| 84.7% | 86% | 84% | 86% | 90% | 85% | 80% | 84% | 87% | 85% | 92% | 81% | 84% | 89% | 85% | 89% | 85% | 78% | 82% | 81% | 83% | 83% | |
| 75.8% | 80% | 77% | 79% | 80% | 84% | 66% | 78% | 68% | 71% | 79% | 74% | 74% | 75% | 67% | 79% | 78% | 67% | 77% | 84% | 72% | 82% | |
| 87.7% | 86% | 89% | 84% | 91% | 82% | 81% | 89% | 90% | 94% | 96% | 87% | 83% | 92% | 89% | 93% | 88% | 83% | 84% | 88% | 87% | 85% |