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 | 1st 87.8% | 6th 84.7% | 4th 85.5% | 6th 84.7% | 19th 80.0% | 18th 80.5% | 15th 82.5% | 20th 78.8% | 12th 83.8% | 13th 83.5% | 5th 85.5% | 16th 82.3% | 14th 83.0% | 17th 80.5% | 3rd 85.8% | 6th 84.7% | 21st 78.0% | 11th 84.0% | 2nd 86.0% | 9th 84.5% | 9th 84.5% | |
| 73.3% | 73% | 72% | 66% | 74% | 66% | 59% | 74% | 77% | 80% | 72% | 79% | 76% | 78% | 78% | 76% | 78% | 71% | 69% | 74% | 79% | 69% | |
| 90.1% | 97% | 89% | 91% | 91% | 86% | 89% | 97% | 89% | 88% | 93% | 97% | 88% | 89% | 90% | 89% | 87% | 85% | 88% | 87% | 86% | 96% | |
| 83.1% | 87% | 88% | 92% | 84% | 91% | 88% | 73% | 72% | 80% | 85% | 80% | 71% | 74% | 72% | 86% | 88% | 71% | 91% | 94% | 85% | 94% | |
| 86.9% | 94% | 90% | 93% | 90% | 77% | 86% | 86% | 77% | 87% | 84% | 86% | 94% | 91% | 82% | 92% | 86% | 85% | 88% | 89% | 88% | 79% |