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 Buddhism. 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 | 8th 83.8% | 10th 83.5% | 18th 79.5% | 12th 82.5% | 17th 79.8% | 19th 77.8% | 14th 81.8% | 16th 80.3% | 19th 77.8% | 5th 85.8% | 4th 86.3% | 21st 73.3% | 1st 88.5% | 15th 81.5% | 2nd 88.3% | 12th 82.5% | 11th 83.5% | 3rd 87.5% | 7th 84.5% | 8th 83.8% | 6th 84.8% | |
| 81.3% | 86% | 78% | 74% | 74% | 79% | 62% | 74% | 86% | 73% | 79% | 91% | 64% | 88% | 92% | 89% | 77% | 95% | 95% | 81% | 90% | 80% | |
| 75.7% | 73% | 77% | 70% | 78% | 68% | 81% | 78% | 70% | 70% | 81% | 78% | 69% | 85% | 70% | 82% | 79% | 74% | 77% | 76% | 76% | 77% | |
| 85.4% | 87% | 92% | 85% | 89% | 84% | 85% | 84% | 79% | 81% | 88% | 85% | 80% | 85% | 82% | 88% | 85% | 82% | 90% | 91% | 84% | 88% | |
| 88.4% | 89% | 87% | 89% | 89% | 88% | 83% | 91% | 86% | 87% | 95% | 91% | 80% | 96% | 82% | 94% | 89% | 83% | 88% | 90% | 85% | 94% |