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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 85.0% | 2nd 84.3% | 6th 82.0% | 6th 82.0% | 20th 71.3% | 8th 81.7% | 10th 81.3% | 19th 76.7% | 11th 81.0% | 5th 82.3% | 18th 78.0% | 14th 79.0% | 14th 79.0% | 16th 78.7% | 21st 57.0% | 9th 81.3% | 13th 79.7% | 3rd 83.7% | 16th 78.7% | 4th 83.3% | 12th 80.7% | |
| 84.5% | 88% | 92% | 95% | 92% | 68% | 90% | 83% | 73% | 84% | 85% | 83% | 91% | 87% | 76% | 84% | 79% | 84% | 91% | 80% | 87% | 83% | |
| 80.4% | 88% | 82% | 79% | 79% | 79% | 79% | 82% | 77% | 83% | 86% | 75% | 70% | 71% | 79% | 87% | 85% | 79% | 79% | 77% | 87% | 85% | |
| 73.2% | 79% | 79% | 72% | 75% | 67% | 76% | 79% | 80% | 76% | 76% | 76% | 76% | 79% | 81% | 0% | 80% | 76% | 81% | 79% | 76% | 74% |