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 | 11th 83.8% | 1st 86.3% | 15th 81.3% | 10th 84.0% | 11th 83.8% | 21st 74.5% | 6th 85.3% | 20th 78.3% | 9th 84.3% | 4th 85.5% | 2nd 86.0% | 18th 80.5% | 4th 85.5% | 3rd 85.8% | 7th 85.0% | 8th 84.8% | 17th 80.8% | 19th 80.3% | 11th 83.8% | 16th 81.2% | 14th 83.0% | |
| 85.0% | 86% | 86% | 74% | 78% | 81% | 71% | 82% | 90% | 85% | 84% | 96% | 82% | 94% | 96% | 82% | 83% | 90% | 88% | 89% | 86% | 83% | |
| 85.4% | 88% | 84% | 86% | 91% | 85% | 80% | 90% | 83% | 93% | 90% | 81% | 84% | 92% | 90% | 86% | 87% | 77% | 78% | 81% | 83% | ||
| 74.4% | 79% | 84% | 81% | 80% | 84% | 66% | 78% | 67% | 67% | 77% | 75% | 73% | 65% | 68% | 78% | 82% | 73% | 65% | 77% | 70% | ||
| 87.0% | 82% | 91% | 84% | 87% | 85% | 81% | 91% | 73% | 92% | 91% | 92% | 83% | 91% | 89% | 94% | 87% | 83% | 90% | 88% | 86% |