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 78.3% | 2nd 81.3% | 1st 81.5% | 4th 79.0% | 11th 77.5% | 20th 71.0% | 16th 73.8% | 12th 76.8% | 10th 77.5% | 19th 72.5% | 3rd 81.0% | 15th 74.8% | 13th 76.8% | 7th 78.3% | 4th 79.0% | 9th 77.8% | 7th 78.3% | 18th 72.5% | 17th 73.3% | 21st 69.8% | 14th 75.8% | |
| 80.4% | 81% | 90% | 80% | 80% | 80% | 61% | 73% | 92% | 81% | 79% | 90% | 88% | 80% | 88% | 80% | 80% | 87% | 73% | 76% | 74% | 76% | |
| 67.0% | 64% | 72% | 74% | 65% | 64% | 70% | 69% | 62% | 65% | 59% | 72% | 55% | 69% | 72% | 70% | 68% | 72% | 70% | 67% | 61% | 67% | |
| 76.5% | 85% | 82% | 85% | 85% | 86% | 74% | 73% | 70% | 81% | 72% | 75% | 78% | 74% | 70% | 79% | 79% | 76% | 62% | 76% | 67% | 78% | |
| 82.0% | 83% | 81% | 87% | 86% | 80% | 79% | 80% | 83% | 83% | 80% | 87% | 78% | 84% | 83% | 87% | 84% | 78% | 85% | 74% | 77% | 82% |