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 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 73.5% | 1st 74.5% | 3rd 74.5% | 8th 69.3% | 4th 74.3% | 19th 63.7% | 11th 67.0% | 17th 64.3% | 12th 66.8% | 20th 63.5% | 16th 64.8% | 9th 68.3% | 15th 65.3% | 10th 67.3% | 6th 73.3% | 1st 74.5% | 14th 65.8% | 7th 69.5% | 17th 64.3% | 13th 66.0% | 21st 63.0% | |
| 65.0% | 70% | 70% | 61% | 61% | 67% | 53% | 70% | 64% | 61% | 61% | 67% | 59% | 68% | 78% | 57% | 69% | 75% | 70% | 61% | 67% | 56% | |
| 77.2% | 72% | 84% | 84% | 72% | 84% | 78% | 78% | 69% | 78% | 72% | 78% | 84% | 80% | 78% | 88% | 73% | 75% | 75% | 78% | 71% | 70% | |
| 60.9% | 68% | 69% | 69% | 75% | 69% | 59% | 59% | 49% | 53% | 59% | 50% | 66% | 48% | 49% | 72% | 79% | 47% | 58% | 54% | 65% | 62% | |
| 69.9% | 84% | 75% | 84% | 69% | 77% | 65% | 61% | 75% | 75% | 62% | 64% | 64% | 65% | 64% | 76% | 77% | 66% | 75% | 64% | 61% | 64% |