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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 10th 80.7% | 4th 84.0% | 5th 83.3% | 6th 83.0% | 18th 75.3% | 16th 75.7% | 11th 80.3% | 3rd 84.3% | 7th 82.3% | 12th 80.0% | 1st 87.3% | 20th 73.7% | 7th 82.3% | 2nd 85.7% | 14th 77.3% | 9th 81.0% | 15th 76.7% | 13th 78.0% | 16th 75.7% | 19th 74.7% | |
| 84.6% | 83% | 83% | 90% | 90% | 82% | 85% | 77% | 88% | 89% | 85% | 89% | 77% | 87% | 94% | 87% | 86% | 79% | 85% | 77% | 79% | |
| 80.7% | 83% | 84% | 84% | 88% | 75% | 81% | 87% | 79% | 82% | 83% | 84% | 73% | 78% | 81% | 82% | 85% | 69% | 77% | 84% | 74% | |
| 75.0% | 76% | 85% | 76% | 71% | 69% | 61% | 77% | 86% | 76% | 72% | 89% | 71% | 82% | 82% | 63% | 72% | 82% | 72% | 66% | 71% |