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 | 6th 84.5% | 1st 88.0% | 9th 83.0% | 9th 83.0% | 12th 82.5% | 7th 84.3% | 18th 81.7% | 21st 78.0% | 8th 83.8% | 4th 85.8% | 5th 84.8% | 13th 82.5% | 3rd 87.3% | 16th 82.2% | 15th 82.3% | 17th 81.8% | 19th 80.8% | 13th 82.5% | 2nd 87.8% | 20th 80.3% | 11th 83.0% | |
| 74.8% | 73% | 76% | 67% | 66% | 78% | 68% | 75% | 74% | 80% | 74% | 81% | 83% | 78% | 85% | 66% | 72% | 79% | 72% | 78% | 74% | 71% | |
| 83.8% | 87% | 87% | 87% | 88% | 82% | 87% | 90% | 71% | 78% | 90% | 87% | 80% | 89% | 83% | 84% | 80% | 86% | 85% | 87% | 76% | 76% | |
| 82.6% | 83% | 92% | 85% | 85% | 91% | 89% | 70% | 77% | 83% | 86% | 76% | 71% | 85% | 71% | 88% | 83% | 71% | 81% | 91% | 85% | 91% | |
| 92.1% | 95% | 97% | 93% | 93% | 79% | 93% | 92% | 90% | 94% | 93% | 95% | 96% | 97% | 90% | 91% | 92% | 87% | 92% | 95% | 86% | 94% |