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 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 | 2nd 86.5% | 7th 84.7% | 1st 87.0% | 5th 85.8% | 14th 82.5% | 16th 80.8% | 20th 79.5% | 16th 80.8% | 9th 84.3% | 3rd 86.5% | 9th 84.3% | 18th 80.5% | 13th 83.0% | 15th 81.5% | 8th 84.5% | 9th 84.3% | 20th 79.5% | 19th 80.3% | 4th 85.8% | 6th 85.0% | 12th 83.0% | |
| 73.9% | 75% | 72% | 75% | 74% | 69% | 59% | 67% | 77% | 80% | 77% | 78% | 76% | 78% | 81% | 76% | 73% | 72% | 68% | 74% | 72% | 79% | |
| 89.9% | 93% | 89% | 91% | 91% | 98% | 89% | 97% | 89% | 88% | 98% | 94% | 88% | 89% | 91% | 87% | 94% | 90% | 82% | 90% | 81% | 79% | |
| 82.2% | 87% | 88% | 92% | 88% | 87% | 88% | 68% | 72% | 82% | 86% | 76% | 71% | 75% | 71% | 85% | 85% | 73% | 83% | 90% | 93% | 87% | |
| 87.2% | 91% | 90% | 90% | 90% | 76% | 87% | 86% | 85% | 87% | 85% | 89% | 87% | 90% | 83% | 90% | 85% | 83% | 88% | 89% | 94% | 87% |