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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 15th 77.5% | 7th 81.8% | 17th 77.0% | 16th 77.3% | 14th 78.0% | 19th 76.3% | 8th 80.8% | 21st 75.0% | 18th 76.8% | 12th 80.0% | 3rd 84.0% | 20th 75.8% | 13th 79.3% | 5th 82.3% | 8th 80.8% | 2nd 84.2% | 10th 80.5% | 11th 80.3% | 1st 85.8% | 4th 83.3% | 6th 82.0% | |
| 77.2% | 76% | 74% | 69% | 69% | 77% | 60% | 73% | 76% | 82% | 76% | 83% | 74% | 80% | 88% | 76% | 84% | 78% | 81% | 83% | 82% | 80% | |
| 86.0% | 74% | 92% | 78% | 78% | 75% | 83% | 96% | 78% | 72% | 89% | 94% | 92% | 83% | 86% | 82% | 94% | 87% | 95% | 92% | 91% | 96% | |
| 68.7% | 70% | 73% | 73% | 73% | 72% | 71% | 66% | 64% | 67% | 69% | 69% | 61% | 65% | 66% | 77% | 69% | 64% | 55% | 72% | 71% | 76% | |
| 87.7% | 90% | 88% | 88% | 89% | 88% | 91% | 88% | 82% | 86% | 86% | 90% | 76% | 89% | 89% | 88% | 90% | 93% | 90% | 96% | 89% | 76% |