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 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 | 14th 77.3% | 4th 82.0% | 16th 76.8% | 14th 77.3% | 17th 76.0% | 12th 78.3% | 10th 79.3% | 21st 72.7% | 20th 73.5% | 18th 75.8% | 2nd 83.5% | 19th 74.5% | 8th 80.0% | 6th 81.5% | 11th 78.7% | 4th 82.0% | 3rd 82.5% | 8th 80.0% | 1st 84.5% | 7th 81.3% | 13th 78.0% | |
| 75.9% | 76% | 74% | 69% | 69% | 77% | 69% | 72% | 71% | 68% | 68% | 83% | 74% | 83% | 88% | 77% | 80% | 81% | 79% | 77% | 79% | 80% | |
| 84.1% | 74% | 92% | 78% | 78% | 86% | 83% | 91% | 78% | 74% | 78% | 92% | 85% | 86% | 83% | 88% | 88% | 85% | 92% | 89% | 82% | ||
| 68.3% | 70% | 73% | 73% | 73% | 64% | 70% | 66% | 60% | 66% | 69% | 69% | 63% | 62% | 66% | 69% | 72% | 65% | 67% | 75% | 74% | ||
| 86.6% | 89% | 89% | 87% | 89% | 77% | 91% | 88% | 82% | 86% | 88% | 90% | 76% | 89% | 89% | 90% | 88% | 96% | 89% | 94% | 76% | 76% |