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 Buddhism. 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 | 5th 85.3% | 4th 86.3% | 13th 83.5% | 17th 80.0% | 16th 80.5% | 20th 78.3% | 7th 85.0% | 15th 82.3% | 18th 79.5% | 19th 78.5% | 9th 84.5% | 11th 84.3% | 1st 88.5% | 21st 75.0% | 3rd 87.0% | 14th 83.0% | 10th 84.5% | 2nd 87.5% | 8th 85.0% | 12th 83.8% | 5th 85.3% | |
| 82.0% | 84% | 91% | 78% | 74% | 73% | 62% | 89% | 74% | 87% | 70% | 74% | 78% | 93% | 70% | 88% | 89% | 88% | 99% | 89% | 80% | 93% | |
| 76.4% | 77% | 77% | 77% | 70% | 67% | 83% | 73% | 78% | 68% | 72% | 86% | 78% | 81% | 70% | 85% | 70% | 77% | 85% | 76% | 77% | 77% | |
| 86.6% | 89% | 88% | 92% | 87% | 97% | 85% | 89% | 86% | 79% | 81% | 97% | 88% | 85% | 80% | 85% | 85% | 87% | 78% | 87% | 91% | 83% | |
| 87.8% | 91% | 89% | 87% | 89% | 85% | 83% | 89% | 91% | 84% | 91% | 81% | 93% | 95% | 80% | 90% | 88% | 86% | 88% | 88% | 87% | 88% |