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 Hinduism. 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 Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | Qwen3 30b A3B Instruct 2507 | Qwen3 Next 80b A3B Instruct | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 79.0% | 5th 77.0% | 4th 77.3% | 1st 80.0% | 7th 75.3% | 13th 69.7% | 8th 74.7% | 10th 73.7% | 6th 76.0% | 10th 73.7% | 9th 74.0% | 12th 70.7% | 3rd 78.0% | |
| 80.4% | 85% | 89% | 84% | 87% | 85% | 69% | 77% | 75% | 86% | 70% | 75% | 77% | 86% | |
| 73.0% | 76% | 73% | 76% | 78% | 71% | 69% | 73% | 73% | 71% | 71% | 72% | 70% | 76% | |
| 72.5% | 76% | 69% | 72% | 75% | 70% | 71% | 74% | 73% | 71% | 80% | 75% | 65% | 72% |