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 3.5 Haiku | Claude Haiku 4.5 | Claude Sonnet 4 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 3 70b Instruct | Llama 4 Maverick | Mistral Large 2411 | Mistral Medium 3 | Mistral Nemo | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o | GPT 4o Mini | GPT OSS 120b | GPT OSS 20b | GLM 4.5 | Qwen3 30b A3B Instruct 2507 | Qwen3 32b | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 86.5% | 14th 81.8% | 7th 84.7% | 1st 87.0% | 13th 82.5% | 16th 80.8% | 10th 83.5% | 20th 79.5% | 16th 80.8% | 8th 84.3% | 5th 85.2% | 3rd 86.5% | 8th 84.3% | 18th 80.5% | 11th 83.0% | 15th 81.5% | 20th 79.5% | 19th 80.3% | 12th 82.5% | 4th 85.8% | 6th 85.0% | |
| 74.4% | 75% | 77% | 72% | 75% | 69% | 59% | 73% | 67% | 77% | 80% | 83% | 77% | 78% | 76% | 78% | 81% | 72% | 68% | 80% | 74% | 72% | |
| 90.2% | 93% | 88% | 89% | 91% | 98% | 89% | 89% | 97% | 89% | 88% | 91% | 98% | 94% | 88% | 89% | 91% | 90% | 82% | 90% | 90% | 81% | |
| 80.5% | 87% | 73% | 88% | 92% | 87% | 88% | 89% | 68% | 72% | 82% | 73% | 86% | 76% | 71% | 75% | 71% | 73% | 83% | 73% | 90% | 93% | |
| 87.3% | 91% | 89% | 90% | 90% | 76% | 87% | 83% | 86% | 85% | 87% | 94% | 85% | 89% | 87% | 90% | 83% | 83% | 88% | 87% | 89% | 94% |