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 | 10th 77.3% | 4th 81.0% | 2nd 82.5% | 7th 78.0% | 16th 74.5% | 13th 75.3% | 14th 75.0% | 9th 77.5% | 12th 76.0% | 19th 73.0% | 1st 82.5% | 5th 80.8% | 17th 73.8% | 6th 79.3% | 8th 77.8% | 3rd 82.3% | 11th 77.0% | 20th 72.5% | 14th 75.0% | 18th 73.5% | 21st 70.7% | |
| 73.9% | 80% | 79% | 80% | 71% | 72% | 62% | 80% | 82% | 67% | 72% | 76% | 80% | 76% | 80% | 67% | 80% | 75% | 66% | 69% | 69% | 68% | |
| 79.0% | 72% | 82% | 81% | 76% | 70% | 78% | 81% | 74% | 78% | 68% | 92% | 92% | 81% | 83% | 78% | 87% | 80% | 72% | 83% | 78% | 72% | |
| 64.6% | 61% | 73% | 73% | 73% | 69% | 65% | 65% | 64% | 63% | 64% | 66% | 61% | 58% | 63% | 69% | 66% | 62% | 54% | 64% | 63% | 61% | |
| 90.2% | 96% | 90% | 96% | 92% | 87% | 96% | 74% | 90% | 96% | 88% | 96% | 90% | 80% | 91% | 97% | 96% | 91% | 98% | 84% | 84% | 82% |