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 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 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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 77.3% | 3rd 77.0% | 5th 76.8% | 6th 76.5% | 1st 80.8% | 7th 75.8% | 18th 68.8% | 19th 68.5% | 12th 72.8% | 12th 72.8% | 3rd 77.0% | 15th 71.8% | 16th 71.3% | 11th 74.0% | 7th 75.8% | 7th 75.8% | 14th 72.0% | 10th 75.5% | 20th 67.5% | 21st 65.7% | 17th 69.5% | |
| 69.4% | 72% | 74% | 66% | 68% | 66% | 67% | 67% | 72% | 71% | 73% | 71% | 72% | 69% | 73% | 74% | 68% | 69% | 74% | 62% | 60% | 69% | |
| 82.0% | 84% | 79% | 85% | 85% | 95% | 83% | 78% | 75% | 78% | 84% | 91% | 83% | 79% | 82% | 81% | 86% | 78% | 81% | 79% | 76% | 79% | |
| 67.8% | 66% | 74% | 68% | 69% | 80% | 70% | 66% | 60% | 67% | 64% | 66% | 66% | 64% | 66% | 73% | 70% | 68% | 68% | 66% | 66% | ||
| 74.7% | 87% | 81% | 88% | 84% | 82% | 83% | 64% | 67% | 75% | 70% | 80% | 66% | 73% | 75% | 75% | 79% | 73% | 79% | 63% | 61% | 64% |