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 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 | 4th 83.0% | 1st 85.3% | 2nd 84.0% | 3rd 83.3% | 21st 72.7% | 15th 78.7% | 12th 79.3% | 19th 77.0% | 5th 82.3% | 11th 80.0% | 9th 80.3% | 13th 79.0% | 9th 80.3% | 14th 78.7% | 18th 77.7% | 16th 78.3% | 6th 82.0% | 20th 76.7% | 8th 81.3% | 7th 81.7% | 17th 78.0% | |
| 85.1% | 88% | 95% | 95% | 92% | 69% | 90% | 82% | 73% | 84% | 79% | 83% | 91% | 89% | 76% | 82% | 79% | 94% | 84% | 89% | 87% | 87% | |
| 79.3% | 84% | 82% | 79% | 82% | 80% | 79% | 82% | 79% | 83% | 86% | 82% | 70% | 71% | 79% | 77% | 82% | 75% | 78% | 76% | 82% | 78% | |
| 75.5% | 77% | 79% | 78% | 76% | 69% | 67% | 74% | 79% | 80% | 75% | 76% | 76% | 81% | 81% | 74% | 74% | 77% | 68% | 79% | 76% | 69% |