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 | 9th 84.0% | 1st 90.3% | 9th 84.0% | 18th 81.3% | 13th 82.8% | 21st 74.5% | 2nd 88.0% | 16th 82.0% | 17th 81.8% | 12th 83.0% | 4th 85.8% | 3rd 87.3% | 7th 84.3% | 18th 81.3% | 7th 84.3% | 5th 85.5% | 15th 82.5% | 20th 79.3% | 5th 85.5% | 14th 82.7% | 11th 83.8% | |
| 86.4% | 88% | 95% | 86% | 74% | 81% | 71% | 93% | 82% | 90% | 86% | 86% | 84% | 92% | 84% | 92% | 96% | 89% | 84% | 94% | 84% | 83% | |
| 84.8% | 84% | 92% | 84% | 86% | 80% | 80% | 87% | 84% | 85% | 85% | 89% | 92% | 81% | 84% | 90% | 90% | 80% | 73% | 84% | 81% | 89% | |
| 75.0% | 78% | 80% | 77% | 81% | 88% | 66% | 80% | 71% | 66% | 67% | 82% | 77% | 75% | 74% | 65% | 67% | 75% | 75% | 76% | 78% | 77% | |
| 87.9% | 86% | 94% | 89% | 84% | 82% | 81% | 92% | 91% | 86% | 94% | 86% | 96% | 89% | 83% | 90% | 89% | 86% | 85% | 88% | 88% | 86% |