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 | 8th 84.3% | 12th 83.3% | 16th 79.3% | 14th 80.5% | 17th 79.0% | 18th 78.8% | 13th 82.5% | 20th 78.0% | 19th 78.3% | 5th 86.0% | 4th 86.3% | 21st 77.3% | 3rd 86.5% | 10th 83.5% | 6th 85.3% | 6th 85.3% | 10th 83.5% | 2nd 86.5% | 8th 84.3% | 1st 88.8% | 14th 80.5% | |
| 80.9% | 84% | 78% | 74% | 74% | 77% | 66% | 74% | 87% | 70% | 81% | 92% | 59% | 88% | 92% | 81% | 84% | 99% | 95% | 83% | 90% | 71% | |
| 75.5% | 77% | 77% | 70% | 70% | 65% | 81% | 78% | 62% | 71% | 80% | 79% | 77% | 85% | 72% | 76% | 79% | 71% | 77% | 76% | 86% | 77% | |
| 85.8% | 87% | 91% | 87% | 89% | 85% | 85% | 87% | 79% | 81% | 90% | 88% | 86% | 81% | 82% | 88% | 87% | 80% | 81% | 91% | 91% | 85% | |
| 88.7% | 89% | 87% | 86% | 89% | 89% | 83% | 91% | 84% | 91% | 93% | 86% | 87% | 92% | 88% | 96% | 91% | 84% | 93% | 87% | 88% | 89% |