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 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 | 6th 81.7% | 4th 82.0% | 9th 81.3% | 2nd 84.0% | 20th 75.7% | 21st 74.7% | 4th 82.0% | 15th 78.7% | 11th 81.0% | 13th 80.7% | 1st 85.7% | 19th 77.7% | 6th 81.7% | 6th 81.7% | 15th 78.7% | 9th 81.3% | 14th 80.3% | 3rd 82.3% | 11th 81.0% | 18th 78.0% | 17th 78.3% | |
| 84.7% | 89% | 89% | 90% | 92% | 73% | 87% | 87% | 71% | 86% | 85% | 88% | 84% | 84% | 83% | 92% | 91% | 84% | 89% | 86% | 79% | 69% | |
| 83.6% | 83% | 83% | 85% | 88% | 85% | 74% | 84% | 83% | 87% | 90% | 82% | 83% | 84% | 88% | 85% | 84% | 85% | 79% | 83% | 81% | 79% | |
| 73.0% | 73% | 74% | 69% | 72% | 69% | 63% | 75% | 82% | 70% | 67% | 87% | 66% | 77% | 74% | 59% | 69% | 72% | 79% | 74% | 74% | 87% |