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 | 9th 83.5% | 14th 82.5% | 17th 79.8% | 13th 82.5% | 7th 85.3% | 20th 77.8% | 15th 81.5% | 21st 76.5% | 18th 79.0% | 11th 83.0% | 4th 86.0% | 19th 78.8% | 1st 87.5% | 10th 83.5% | 6th 86.0% | 4th 86.0% | 12th 83.0% | 2nd 87.0% | 3rd 86.3% | 8th 84.5% | 16th 80.8% | |
| 81.6% | 81% | 78% | 74% | 74% | 81% | 62% | 71% | 87% | 73% | 71% | 91% | 70% | 92% | 90% | 84% | 90% | 92% | 99% | 90% | 92% | 71% | |
| 75.5% | 77% | 77% | 70% | 78% | 71% | 81% | 78% | 62% | 67% | 80% | 77% | 73% | 85% | 71% | 79% | 76% | 77% | 77% | 76% | 77% | 77% | |
| 86.0% | 87% | 91% | 86% | 89% | 97% | 85% | 86% | 78% | 81% | 88% | 85% | 85% | 85% | 82% | 88% | 87% | 78% | 84% | 91% | 84% | 88% | |
| 88.5% | 89% | 84% | 89% | 89% | 92% | 83% | 91% | 79% | 95% | 93% | 91% | 87% | 88% | 91% | 93% | 91% | 85% | 88% | 88% | 85% | 87% |