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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 77.3% | 2nd 79.0% | 6th 75.5% | 5th 76.5% | 1st 80.5% | 8th 73.5% | 15th 69.8% | 15th 69.8% | 8th 73.5% | 10th 72.0% | 4th 76.5% | 18th 69.0% | 12th 70.8% | 14th 70.3% | 21st 40.3% | 7th 74.3% | 11th 71.0% | 19th 67.8% | 17th 69.3% | 20th 61.7% | 13th 70.5% | |
| 69.1% | 71% | 74% | 68% | 68% | 66% | 57% | 67% | 74% | 71% | 71% | 71% | 73% | 70% | 73% | 80% | 69% | 67% | 73% | 62% | 59% | 68% | |
| 78.1% | 86% | 79% | 85% | 85% | 95% | 84% | 82% | 79% | 80% | 83% | 87% | 84% | 78% | 82% | 0% | 83% | 83% | 78% | 84% | 71% | 73% | |
| 62.1% | 66% | 82% | 68% | 69% | 79% | 70% | 66% | 57% | 68% | 67% | 66% | 53% | 64% | 58% | 0% | 70% | 68% | 41% | 66% | 57% | 69% | |
| 74.1% | 86% | 81% | 81% | 84% | 82% | 83% | 64% | 69% | 75% | 67% | 82% | 66% | 71% | 68% | 81% | 75% | 66% | 79% | 65% | 60% | 72% |