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 | 3rd 73.5% | 1st 76.0% | 2nd 75.0% | 10th 69.8% | 4th 73.0% | 19th 62.5% | 8th 70.0% | 17th 64.0% | 11th 69.5% | 21st 59.3% | 7th 70.3% | 17th 64.0% | 12th 69.0% | 5th 71.0% | 9th 70.0% | 6th 71.0% | 13th 68.5% | 20th 61.5% | 16th 64.3% | 15th 64.8% | 14th 65.5% | |
| 65.1% | 70% | 70% | 70% | 61% | 67% | 56% | 70% | 64% | 59% | 55% | 73% | 55% | 74% | 78% | 57% | 62% | 75% | 62% | 61% | 65% | 63% | |
| 75.8% | 73% | 81% | 84% | 72% | 84% | 70% | 78% | 69% | 78% | 61% | 78% | 84% | 80% | 78% | 75% | 78% | 75% | 75% | 78% | 70% | 70% | |
| 61.4% | 68% | 78% | 69% | 75% | 64% | 59% | 68% | 54% | 66% | 59% | 61% | 56% | 57% | 55% | 72% | 72% | 56% | 26% | 54% | 52% | 68% | |
| 70.6% | 83% | 75% | 77% | 71% | 77% | 65% | 64% | 69% | 75% | 62% | 69% | 61% | 65% | 73% | 76% | 72% | 68% | 83% | 64% | 72% | 61% |