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 | 6th 85.3% | 12th 83.3% | 16th 80.0% | 6th 85.3% | 18th 79.0% | 20th 75.5% | 15th 82.3% | 17th 79.5% | 19th 78.0% | 10th 84.3% | 4th 87.3% | 21st 75.5% | 1st 88.5% | 13th 83.2% | 6th 85.3% | 11th 84.0% | 9th 84.5% | 2nd 87.8% | 5th 86.5% | 2nd 87.8% | 14th 83.0% | |
| 82.0% | 84% | 78% | 74% | 77% | 80% | 62% | 74% | 87% | 72% | 81% | 92% | 64% | 88% | 90% | 80% | 83% | 92% | 92% | 89% | 99% | 83% | |
| 75.4% | 77% | 77% | 70% | 78% | 64% | 72% | 78% | 68% | 72% | 75% | 78% | 72% | 85% | 71% | 79% | 76% | 77% | 84% | 76% | 77% | 77% | |
| 86.3% | 87% | 91% | 87% | 97% | 84% | 85% | 86% | 79% | 81% | 88% | 88% | 86% | 87% | 84% | 84% | 86% | 84% | 87% | 91% | 87% | 83% | |
| 88.9% | 93% | 87% | 89% | 89% | 88% | 83% | 91% | 84% | 87% | 93% | 91% | 80% | 94% | 88% | 98% | 91% | 85% | 88% | 90% | 88% | 89% |