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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 5th 77.3% | 4th 78.0% | 3rd 79.0% | 1st 80.7% | 8th 74.7% | 16th 71.7% | 12th 73.0% | 19th 67.3% | 6th 76.0% | 15th 71.7% | 10th 73.7% | 13th 72.0% | 11th 73.3% | 7th 75.0% | 21st 51.7% | 2nd 80.0% | 13th 72.0% | 9th 74.3% | 18th 68.0% | 20th 66.3% | 17th 71.0% | |
| 91.8% | 89% | 91% | 98% | 98% | 93% | 94% | 85% | 94% | 97% | 90% | 93% | 87% | 91% | 96% | 95% | 95% | 94% | 88% | 87% | 87% | 86% | |
| 53.2% | 67% | 67% | 65% | 70% | 57% | 53% | 59% | 39% | 63% | 53% | 48% | 48% | 50% | 50% | 0% | 68% | 43% | 59% | 53% | 46% | 59% | |
| 73.1% | 76% | 76% | 74% | 74% | 74% | 68% | 75% | 69% | 68% | 72% | 80% | 81% | 79% | 79% | 60% | 77% | 79% | 76% | 64% | 66% | 68% |