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 | 15th 77.3% | 4th 81.8% | 16th 77.0% | 14th 77.3% | 20th 73.8% | 18th 76.0% | 13th 78.0% | 19th 75.0% | 11th 79.0% | 17th 76.3% | 2nd 84.0% | 21st 73.3% | 7th 80.3% | 3rd 82.0% | 1st 84.7% | 8th 80.3% | 6th 80.5% | 10th 79.8% | 5th 80.8% | 8th 80.3% | 12th 78.0% | |
| 75.8% | 78% | 74% | 69% | 69% | 77% | 60% | 72% | 71% | 82% | 72% | 83% | 74% | 77% | 83% | 83% | 76% | 78% | 75% | 77% | 82% | 80% | |
| 84.5% | 74% | 92% | 78% | 78% | 75% | 83% | 91% | 79% | 78% | 78% | 94% | 82% | 89% | 86% | 93% | 83% | 92% | 89% | 86% | 92% | 82% | |
| 68.3% | 69% | 73% | 73% | 73% | 66% | 70% | 61% | 64% | 70% | 69% | 69% | 61% | 66% | 66% | 75% | 74% | 59% | 57% | 75% | 71% | 74% | |
| 86.6% | 88% | 88% | 88% | 89% | 77% | 91% | 88% | 86% | 86% | 86% | 90% | 76% | 89% | 93% | 88% | 88% | 93% | 98% | 85% | 76% | 76% |