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 80.3% | 1st 84.5% | 4th 81.3% | 2nd 82.3% | 5th 81.0% | 13th 78.5% | 6th 80.8% | 15th 77.3% | 3rd 81.8% | 17th 76.3% | 7th 80.7% | 11th 79.8% | 16th 76.8% | 8th 80.3% | 10th 80.0% | 12th 79.0% | 21st 73.8% | 19th 75.3% | 14th 77.5% | 20th 74.8% | 18th 76.0% | |
| 82.4% | 79% | 87% | 79% | 76% | 84% | 83% | 83% | 86% | 87% | 75% | 86% | 88% | 86% | 90% | 70% | 79% | 84% | 84% | 81% | 79% | 85% | |
| 80.9% | 81% | 84% | 87% | 84% | 88% | 71% | 85% | 81% | 85% | 83% | 84% | 81% | 76% | 84% | 85% | 78% | 73% | 73% | 77% | 80% | 79% | |
| 73.2% | 84% | 84% | 78% | 85% | 74% | 79% | 73% | 61% | 73% | 71% | 73% | 73% | 69% | 64% | 86% | 79% | 61% | 61% | 73% | 64% | 73% | |
| 79.1% | 77% | 83% | 81% | 84% | 78% | 81% | 82% | 81% | 82% | 76% | 80% | 77% | 76% | 83% | 79% | 80% | 77% | 83% | 79% | 76% | 67% |