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 Judaism. 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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 82.3% | 13th 78.0% | 12th 78.3% | 15th 77.7% | 1st 84.0% | 20th 70.0% | 4th 82.0% | 7th 81.0% | 18th 75.7% | 8th 79.7% | 11th 79.0% | 13th 78.0% | 4th 82.0% | 6th 81.3% | 21st 50.7% | 17th 76.3% | 9th 79.3% | 16th 76.7% | 2nd 83.0% | 19th 74.7% | 9th 79.3% | |
| 79.1% | 86% | 73% | 74% | 74% | 88% | 68% | 86% | 89% | 81% | 84% | 76% | 79% | 87% | 75% | 78% | 81% | 81% | 79% | 77% | 81% | 64% | |
| 72.0% | 74% | 74% | 79% | 80% | 83% | 69% | 72% | 69% | 64% | 71% | 73% | 69% | 67% | 71% | 74% | 73% | 69% | 64% | 81% | 59% | 78% | |
| 81.6% | 87% | 87% | 82% | 79% | 81% | 73% | 88% | 85% | 82% | 84% | 88% | 86% | 92% | 98% | 0% | 75% | 88% | 87% | 91% | 84% | 96% |