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 | 17th 75.8% | 5th 82.0% | 14th 77.3% | 14th 77.3% | 21st 72.0% | 16th 77.3% | 12th 79.3% | 20th 73.3% | 18th 75.3% | 13th 78.3% | 1st 84.8% | 19th 74.5% | 9th 80.8% | 3rd 83.3% | 2nd 83.7% | 8th 81.0% | 4th 82.3% | 10th 80.3% | 7th 81.5% | 5th 82.0% | 11th 80.0% | |
| 75.5% | 70% | 74% | 69% | 69% | 77% | 62% | 72% | 69% | 68% | 72% | 88% | 74% | 80% | 88% | 84% | 77% | 81% | 76% | 76% | 80% | 80% | |
| 85.1% | 74% | 92% | 78% | 78% | 75% | 83% | 91% | 78% | 74% | 86% | 92% | 85% | 89% | 86% | 94% | 89% | 90% | 89% | 86% | 88% | 90% | |
| 68.8% | 70% | 73% | 73% | 73% | 64% | 73% | 66% | 60% | 70% | 69% | 69% | 63% | 65% | 66% | 69% | 69% | 64% | 67% | 75% | 72% | 74% | |
| 87.1% | 89% | 89% | 89% | 89% | 72% | 91% | 88% | 86% | 89% | 86% | 90% | 76% | 89% | 93% | 88% | 89% | 94% | 89% | 89% | 88% | 76% |