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 | 8th 84.7% | 5th 85.3% | 15th 82.3% | 12th 83.3% | 20th 75.7% | 21st 75.3% | 10th 84.0% | 19th 79.7% | 7th 85.0% | 12th 83.3% | 2nd 86.0% | 2nd 86.0% | 14th 82.3% | 5th 85.3% | 18th 81.0% | 15th 82.3% | 10th 84.0% | 17th 81.7% | 8th 84.7% | 1st 92.0% | 2nd 86.0% | |
| 86.4% | 85% | 89% | 89% | 89% | 72% | 77% | 89% | 79% | 89% | 92% | 89% | 88% | 89% | 88% | 93% | 85% | 82% | 83% | 86% | 94% | ||
| 81.3% | 87% | 86% | 84% | 85% | 79% | 75% | 80% | 75% | 79% | 85% | 82% | 78% | 73% | 77% | 86% | 82% | 81% | 77% | 83% | 93% | 80% | |
| 82.1% | 82% | 81% | 74% | 76% | 76% | 74% | 83% | 85% | 87% | 73% | 87% | 92% | 85% | 91% | 64% | 80% | 89% | 85% | 85% | 91% | 84% |