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 86.3% | 6th 84.7% | 5th 84.8% | 6th 84.7% | 9th 83.8% | 15th 81.0% | 18th 80.3% | 20th 77.7% | 9th 83.8% | 12th 83.3% | 8th 84.3% | 19th 80.3% | 14th 81.3% | 16th 80.8% | 2nd 86.3% | 11th 83.5% | 21st 77.5% | 4th 85.0% | 1st 86.8% | 13th 82.5% | 17th 80.5% | |
| 73.2% | 78% | 72% | 66% | 74% | 66% | 59% | 67% | 76% | 80% | 72% | 78% | 76% | 75% | 78% | 74% | 73% | 72% | 77% | 77% | 68% | 79% | |
| 89.5% | 94% | 89% | 91% | 91% | 96% | 89% | 99% | 91% | 88% | 92% | 94% | 88% | 89% | 91% | 92% | 85% | 86% | 82% | 91% | 82% | 79% | |
| 81.3% | 84% | 88% | 92% | 84% | 87% | 89% | 68% | 72% | 79% | 85% | 76% | 71% | 71% | 72% | 92% | 88% | 70% | 88% | 90% | 92% | 69% | |
| 87.2% | 89% | 90% | 90% | 90% | 86% | 87% | 87% | 72% | 88% | 84% | 89% | 86% | 90% | 82% | 87% | 88% | 82% | 93% | 89% | 88% | 95% |