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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 4th 85.3% | 1st 89.8% | 9th 84.0% | 16th 81.3% | 14th 82.8% | 21st 73.5% | 2nd 87.3% | 9th 84.0% | 20th 80.0% | 13th 83.5% | 5th 85.0% | 3rd 86.8% | 11th 83.8% | 17th 80.8% | 7th 84.3% | 7th 84.3% | 19th 80.3% | 18th 80.5% | 6th 84.5% | 11th 83.8% | 15th 82.0% | |
| 85.1% | 86% | 95% | 86% | 74% | 81% | 71% | 93% | 82% | 86% | 86% | 86% | 78% | 92% | 82% | 92% | 96% | 80% | 84% | 89% | 89% | 80% | |
| 84.8% | 86% | 90% | 84% | 86% | 85% | 80% | 90% | 84% | 84% | 85% | 86% | 93% | 77% | 84% | 89% | 88% | 78% | 78% | 86% | 81% | 86% | |
| 75.1% | 78% | 80% | 77% | 81% | 82% | 62% | 79% | 78% | 65% | 71% | 82% | 80% | 75% | 74% | 64% | 64% | 75% | 77% | 77% | 77% | 79% | |
| 87.8% | 91% | 94% | 89% | 84% | 83% | 81% | 87% | 92% | 85% | 92% | 86% | 96% | 91% | 83% | 92% | 89% | 88% | 83% | 86% | 88% | 83% |