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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 7th 83.7% | 5th 85.0% | 12th 82.3% | 16th 81.3% | 13th 82.0% | 20th 76.3% | 16th 81.3% | 18th 78.7% | 4th 85.0% | 13th 82.0% | 3rd 85.7% | 8th 83.7% | 11th 83.3% | 8th 83.7% | 19th 78.0% | 13th 82.0% | 8th 83.7% | 21st 73.3% | 5th 85.0% | 1st 86.7% | 1st 86.7% | |
| 85.3% | 85% | 89% | 89% | 89% | 85% | 80% | 83% | 76% | 89% | 85% | 88% | 82% | 89% | 88% | 89% | 87% | 89% | 57% | 86% | 93% | 93% | |
| 80.7% | 81% | 86% | 84% | 85% | 85% | 75% | 80% | 75% | 79% | 85% | 82% | 77% | 76% | 77% | 85% | 84% | 65% | 77% | 83% | 80% | 93% | |
| 81.1% | 85% | 80% | 74% | 70% | 76% | 74% | 81% | 85% | 87% | 76% | 87% | 92% | 85% | 86% | 60% | 75% | 97% | 86% | 86% | 87% | 74% |