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 | 11th 84.0% | 1st 89.8% | 5th 86.3% | 17th 81.3% | 10th 84.3% | 21st 74.5% | 2nd 88.0% | 14th 83.3% | 19th 80.3% | 8th 84.8% | 9th 84.7% | 13th 83.8% | 7th 85.0% | 18th 81.0% | 11th 84.0% | 6th 85.0% | 20th 80.0% | 15th 83.0% | 4th 86.8% | 2nd 88.0% | 16th 81.8% | |
| 86.8% | 88% | 95% | 88% | 74% | 85% | 71% | 93% | 82% | 86% | 89% | 90% | 78% | 92% | 82% | 93% | 96% | 88% | 84% | 98% | 92% | 78% | |
| 85.2% | 86% | 91% | 84% | 86% | 87% | 80% | 90% | 84% | 84% | 85% | 81% | 90% | 81% | 84% | 90% | 87% | 76% | 85% | 88% | 88% | 83% | |
| 75.9% | 76% | 79% | 84% | 81% | 88% | 66% | 80% | 78% | 65% | 71% | 82% | 75% | 79% | 74% | 65% | 68% | 70% | 77% | 71% | 84% | 81% | |
| 87.2% | 86% | 94% | 89% | 84% | 77% | 81% | 89% | 89% | 86% | 94% | 86% | 92% | 88% | 84% | 88% | 89% | 86% | 86% | 90% | 88% | 85% |