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 78.0% | 2nd 80.0% | 5th 77.0% | 3rd 78.3% | 1st 82.7% | 13th 72.0% | 20th 68.7% | 16th 71.7% | 6th 75.7% | 10th 73.3% | 7th 75.7% | 13th 72.0% | 11th 73.0% | 13th 72.0% | 9th 74.3% | 8th 75.3% | 12th 72.7% | 17th 71.0% | 19th 69.7% | 21st 68.0% | 18th 70.0% | |
| 79.2% | 90% | 84% | 89% | 84% | 90% | 85% | 66% | 74% | 80% | 78% | 84% | 70% | 71% | 78% | 80% | 79% | 77% | 83% | 75% | 77% | 69% | |
| 70.2% | 70% | 80% | 73% | 79% | 78% | 71% | 69% | 68% | 73% | 68% | 71% | 71% | 67% | 62% | 76% | 73% | 70% | 56% | 70% | 60% | 69% | |
| 72.2% | 74% | 76% | 69% | 72% | 80% | 60% | 71% | 73% | 74% | 74% | 72% | 75% | 81% | 76% | 67% | 74% | 71% | 74% | 64% | 67% | 72% |