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 85.0% | 4th 83.3% | 3rd 84.7% | 13th 73.0% | 6th 81.7% | 8th 80.3% | 5th 83.0% | 8th 80.3% | 12th 78.3% | 7th 80.7% | 11th 79.0% | 1st 85.7% | 10th 80.0% | |
| 85.2% | 92% | 93% | 92% | 69% | 90% | 82% | 84% | 79% | 83% | 91% | 77% | 93% | 82% | |
| 81.2% | 84% | 79% | 87% | 82% | 79% | 82% | 85% | 84% | 76% | 70% | 79% | 85% | 84% | |
| 77.1% | 79% | 78% | 75% | 68% | 76% | 77% | 80% | 78% | 76% | 81% | 81% | 79% | 74% |