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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 7th 85.5% | 10th 82.8% | 17th 79.3% | 8th 84.3% | 19th 77.8% | 21st 75.5% | 12th 82.3% | 18th 79.0% | 16th 79.5% | 5th 86.3% | 3rd 87.3% | 15th 80.8% | 1st 88.3% | 11th 82.5% | 9th 83.3% | 5th 86.3% | 13th 82.0% | 14th 81.3% | 4th 86.5% | 2nd 87.8% | 20th 76.5% | |
| 81.7% | 86% | 78% | 74% | 71% | 77% | 62% | 74% | 87% | 74% | 81% | 92% | 70% | 92% | 91% | 79% | 90% | 91% | 77% | 90% | 99% | 80% | |
| 75.7% | 77% | 77% | 67% | 80% | 65% | 72% | 78% | 68% | 67% | 81% | 81% | 86% | 85% | 70% | 79% | 78% | 72% | 77% | 76% | 77% | 77% | |
| 85.7% | 88% | 92% | 87% | 97% | 84% | 85% | 86% | 80% | 81% | 88% | 85% | 80% | 83% | 82% | 88% | 87% | 81% | 84% | 91% | 87% | 84% | |
| 87.2% | 91% | 84% | 89% | 89% | 85% | 83% | 91% | 81% | 96% | 95% | 91% | 87% | 93% | 87% | 87% | 90% | 84% | 87% | 89% | 88% | 65% |