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 | 16th 73.5% | 2nd 81.0% | 3rd 80.3% | 6th 78.0% | 13th 75.0% | 18th 73.0% | 18th 73.0% | 15th 73.8% | 12th 75.3% | 10th 75.5% | 1st 81.0% | 8th 76.8% | 10th 75.5% | 7th 77.5% | 21st 35.3% | 4th 79.8% | 5th 79.3% | 9th 76.3% | 14th 74.5% | 20th 71.7% | 16th 73.5% | |
| 72.9% | 75% | 79% | 71% | 71% | 68% | 56% | 80% | 71% | 67% | 68% | 76% | 80% | 80% | 76% | 67% | 79% | 77% | 77% | 69% | 69% | 74% | |
| 74.4% | 65% | 82% | 81% | 76% | 71% | 81% | 81% | 70% | 78% | 86% | 88% | 74% | 81% | 83% | 0% | 82% | 79% | 75% | 81% | 75% | 73% | |
| 63.7% | 61% | 73% | 73% | 73% | 65% | 61% | 57% | 64% | 63% | 60% | 64% | 61% | 58% | 55% | 74% | 65% | 63% | 61% | 64% | 61% | 61% | |
| 86.1% | 93% | 90% | 96% | 92% | 96% | 94% | 74% | 90% | 93% | 88% | 96% | 92% | 83% | 96% | 0% | 93% | 98% | 92% | 84% | 82% | 86% |