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 | Grok 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 10th 81.7% | 9th 82.0% | 14th 80.0% | 2nd 84.0% | 15th 79.3% | 21st 74.7% | 5th 82.7% | 17th 78.7% | 12th 80.3% | 16th 79.0% | 1st 86.0% | 19th 76.7% | 10th 81.7% | 5th 82.7% | 20th 76.3% | 2nd 84.0% | 8th 82.3% | 5th 82.7% | 4th 83.0% | 12th 80.3% | 18th 77.0% | |
| 84.9% | 90% | 89% | 90% | 92% | 86% | 87% | 87% | 71% | 86% | 82% | 89% | 84% | 84% | 83% | 84% | 94% | 81% | 79% | 86% | 79% | 79% | |
| 82.7% | 82% | 83% | 85% | 88% | 85% | 74% | 84% | 82% | 85% | 88% | 82% | 80% | 84% | 88% | 79% | 87% | 79% | 80% | 82% | 80% | 79% | |
| 74.6% | 73% | 74% | 65% | 72% | 67% | 63% | 77% | 83% | 70% | 67% | 87% | 66% | 77% | 77% | 66% | 71% | 87% | 89% | 81% | 82% | 73% |