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 Christianity. 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 | 5th 86.3% | 1st 88.8% | 6th 85.5% | 15th 82.5% | 15th 82.5% | 8th 84.3% | 18th 82.0% | 19th 82.0% | 9th 84.0% | 11th 83.5% | 12th 83.2% | 10th 83.7% | 3rd 86.8% | 17th 82.3% | 20th 81.5% | 4th 86.5% | 13th 83.0% | 7th 84.7% | 1st 88.8% | 14th 82.8% | 21st 75.3% | |
| 76.3% | 78% | 76% | 66% | 66% | 79% | 68% | 76% | 77% | 77% | 73% | 81% | 83% | 86% | 85% | 65% | 83% | 75% | 74% | 83% | 76% | 76% | |
| 85.0% | 88% | 90% | 87% | 89% | 82% | 87% | 90% | 85% | 78% | 83% | 86% | 85% | 89% | 82% | 87% | 89% | 86% | 85% | 83% | 79% | 76% | |
| 82.9% | 85% | 92% | 93% | 85% | 92% | 89% | 70% | 76% | 88% | 86% | 76% | 71% | 75% | 73% | 81% | 84% | 82% | 88% | 93% | 82% | 79% | |
| 91.0% | 94% | 97% | 96% | 90% | 77% | 93% | 92% | 90% | 93% | 92% | 90% | 96% | 97% | 89% | 93% | 90% | 89% | 92% | 96% | 94% | 70% |