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 | 14th 81.7% | 6th 85.3% | 13th 82.3% | 11th 83.3% | 15th 81.3% | 21st 76.3% | 19th 80.0% | 20th 78.0% | 8th 84.7% | 10th 83.7% | 5th 85.7% | 2nd 87.0% | 12th 82.7% | 7th 85.0% | 18th 80.3% | 15th 81.3% | 17th 80.7% | 4th 85.7% | 8th 84.7% | 1st 88.7% | 2nd 87.0% | |
| 86.9% | 85% | 89% | 89% | 89% | 85% | 80% | 83% | 76% | 89% | 93% | 88% | 92% | 89% | 88% | 88% | 84% | 77% | 93% | 86% | 93% | 89% | |
| 80.7% | 84% | 86% | 84% | 87% | 83% | 75% | 80% | 75% | 79% | 82% | 82% | 77% | 73% | 76% | 85% | 82% | 75% | 73% | 83% | 87% | 86% | |
| 81.8% | 76% | 81% | 74% | 74% | 76% | 74% | 77% | 83% | 86% | 76% | 87% | 92% | 86% | 91% | 68% | 78% | 90% | 91% | 85% | 86% | 86% |