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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 10th 79.7% | 2nd 82.7% | 5th 81.3% | 9th 80.3% | 8th 80.7% | 19th 75.0% | 16th 77.0% | 1st 84.3% | 6th 81.3% | 18th 75.7% | 13th 79.0% | 3rd 82.0% | 15th 77.7% | 7th 81.0% | 20th 73.0% | 12th 79.0% | 14th 78.0% | 3rd 82.0% | 11th 79.3% | 21st 70.3% | 17th 76.7% | |
| 81.0% | 80% | 82% | 84% | 84% | 85% | 78% | 77% | 89% | 84% | 78% | 82% | 78% | 77% | 85% | 82% | 84% | 79% | 84% | 79% | 73% | 78% | |
| 75.5% | 79% | 80% | 80% | 83% | 79% | 71% | 73% | 75% | 78% | 77% | 69% | 81% | 70% | 71% | 77% | 76% | 70% | 76% | 79% | 65% | 77% | |
| 80.0% | 80% | 86% | 80% | 74% | 78% | 76% | 81% | 89% | 82% | 72% | 86% | 87% | 86% | 87% | 60% | 77% | 85% | 86% | 80% | 73% | 75% |