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 Hinduism. 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 | 4th 82.7% | 1st 85.7% | 10th 80.3% | 3rd 83.0% | 17th 77.0% | 7th 81.7% | 10th 80.3% | 20th 74.3% | 15th 78.3% | 6th 82.3% | 8th 81.3% | 12th 79.0% | 16th 78.0% | 14th 78.3% | 4th 82.7% | 12th 79.0% | 18th 76.7% | 20th 74.3% | 2nd 84.3% | 18th 76.7% | 8th 81.3% | |
| 84.9% | 88% | 95% | 93% | 92% | 76% | 90% | 82% | 73% | 76% | 84% | 83% | 91% | 87% | 76% | 85% | 82% | 82% | 90% | 89% | 81% | 87% | |
| 79.0% | 79% | 83% | 79% | 79% | 85% | 79% | 82% | 71% | 83% | 83% | 80% | 70% | 69% | 80% | 85% | 80% | 76% | 66% | 85% | 82% | 82% | |
| 75.8% | 81% | 79% | 69% | 78% | 70% | 76% | 77% | 79% | 76% | 80% | 81% | 76% | 78% | 79% | 78% | 75% | 72% | 67% | 79% | 67% | 75% |