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 Other religious group. Source: Global Dialogues GD2 (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 | 8th 76.7% | 2nd 79.0% | 9th 76.0% | 4th 78.0% | 11th 75.3% | 18th 72.0% | 15th 74.0% | 17th 72.7% | 11th 75.3% | 15th 74.0% | 4th 78.0% | 6th 77.7% | 6th 77.7% | 10th 75.7% | 1st 80.0% | 3rd 78.7% | 14th 75.0% | 21st 68.0% | 20th 70.3% | 11th 75.3% | 19th 71.3% | |
| 87.0% | 91% | 91% | 84% | 91% | 93% | 87% | 85% | 80% | 93% | 91% | 91% | 85% | 93% | 86% | 86% | 94% | 84% | 83% | 72% | 94% | 72% | |
| 62.6% | 63% | 69% | 70% | 69% | 59% | 62% | 59% | 58% | 62% | 61% | 64% | 63% | 59% | 54% | 70% | 70% | 62% | 48% | 63% | 63% | 66% | |
| 76.3% | 76% | 77% | 74% | 74% | 74% | 67% | 78% | 80% | 71% | 70% | 79% | 85% | 81% | 87% | 84% | 72% | 79% | 73% | 76% | 69% | 76% |