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 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 | Grok 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 9th 79.7% | 1st 83.7% | 4th 80.3% | 4th 80.3% | 6th 80.0% | 20th 75.0% | 15th 77.7% | 12th 78.0% | 6th 80.0% | 17th 77.0% | 2nd 82.0% | 6th 80.0% | 18th 76.3% | 3rd 81.3% | 15th 77.7% | 12th 78.0% | 12th 78.0% | 11th 78.7% | 10th 79.0% | 21st 73.7% | 19th 75.7% | |
| 80.8% | 82% | 82% | 84% | 84% | 85% | 78% | 77% | 77% | 82% | 85% | 84% | 78% | 77% | 86% | 80% | 80% | 76% | 82% | 79% | 76% | 82% | |
| 75.2% | 78% | 80% | 81% | 83% | 76% | 71% | 75% | 70% | 76% | 72% | 77% | 75% | 70% | 71% | 81% | 78% | 73% | 71% | 78% | 68% | 75% | |
| 80.0% | 79% | 89% | 76% | 74% | 79% | 76% | 81% | 87% | 82% | 74% | 85% | 87% | 82% | 87% | 72% | 76% | 85% | 83% | 80% | 77% | 70% |