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 | 3rd 85.2% | 5th 84.7% | 1st 87.0% | 5th 84.7% | 21st 78.3% | 16th 80.5% | 17th 80.3% | 19th 79.3% | 10th 84.3% | 2nd 85.3% | 11th 83.8% | 13th 82.3% | 14th 82.0% | 18th 80.0% | 12th 83.7% | 7th 84.5% | 20th 78.5% | 14th 82.0% | 4th 85.0% | 7th 84.5% | 9th 84.5% | |
| 73.5% | 74% | 72% | 75% | 74% | 69% | 59% | 67% | 77% | 80% | 76% | 78% | 76% | 74% | 78% | 75% | 72% | 72% | 71% | 74% | 79% | 71% | |
| 88.4% | 93% | 89% | 91% | 91% | 81% | 89% | 97% | 84% | 88% | 93% | 89% | 88% | 89% | 90% | 84% | 88% | 86% | 85% | 87% | 79% | 96% | |
| 82.3% | 84% | 88% | 92% | 84% | 87% | 87% | 71% | 72% | 82% | 85% | 79% | 71% | 74% | 73% | 90% | 89% | 70% | 83% | 90% | 93% | 85% | |
| 87.2% | 90% | 90% | 90% | 90% | 76% | 87% | 86% | 84% | 87% | 87% | 89% | 94% | 91% | 79% | 86% | 89% | 86% | 89% | 89% | 87% | 86% |