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 | 8th 84.7% | 9th 84.5% | 17th 81.3% | 3rd 85.0% | 15th 81.8% | 21st 74.5% | 11th 84.3% | 16th 81.5% | 13th 83.8% | 7th 84.8% | 11th 84.3% | 18th 81.0% | 5th 85.0% | 9th 84.5% | 3rd 85.0% | 2nd 86.5% | 19th 77.3% | 20th 77.3% | 1st 87.0% | 14th 82.5% | 5th 85.0% | |
| 83.9% | 82% | 86% | 74% | 78% | 81% | 71% | 84% | 86% | 89% | 78% | 92% | 82% | 94% | 98% | 76% | 85% | 89% | 79% | 92% | 83% | 82% | |
| 84.3% | 88% | 84% | 86% | 91% | 78% | 80% | 84% | 86% | 85% | 90% | 81% | 84% | 90% | 84% | 94% | 87% | 73% | 73% | 81% | 84% | 87% | |
| 75.3% | 83% | 77% | 81% | 80% | 86% | 66% | 78% | 65% | 67% | 75% | 75% | 74% | 64% | 67% | 79% | 86% | 66% | 67% | 84% | 77% | 85% | |
| 88.2% | 86% | 91% | 84% | 91% | 82% | 81% | 91% | 89% | 94% | 96% | 89% | 84% | 92% | 89% | 91% | 88% | 81% | 90% | 91% | 86% | 86% |