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 | 5th 77.0% | 4th 78.0% | 3rd 79.0% | 1st 80.3% | 7th 74.7% | 13th 71.3% | 20th 67.7% | 21st 66.0% | 7th 74.7% | 15th 70.0% | 10th 73.0% | 11th 72.0% | 11th 72.0% | 7th 74.7% | 6th 75.3% | 2nd 79.7% | 17th 69.3% | 14th 71.0% | 16th 70.0% | 18th 68.7% | 19th 68.3% | |
| 91.5% | 89% | 91% | 98% | 97% | 93% | 94% | 81% | 87% | 97% | 90% | 96% | 87% | 93% | 96% | 97% | 98% | 88% | 93% | 87% | 82% | 88% | |
| 54.8% | 67% | 67% | 65% | 70% | 57% | 53% | 47% | 43% | 59% | 53% | 48% | 48% | 47% | 50% | 64% | 65% | 46% | 42% | 53% | 54% | 52% | |
| 72.7% | 75% | 76% | 74% | 74% | 74% | 67% | 75% | 68% | 68% | 67% | 75% | 81% | 76% | 78% | 65% | 76% | 74% | 78% | 70% | 70% | 65% |