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 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 | 13th 80.0% | 3rd 83.3% | 3rd 83.3% | 5th 83.0% | 15th 77.3% | 20th 74.7% | 14th 78.0% | 7th 82.7% | 8th 82.3% | 9th 82.0% | 1st 85.7% | 16th 77.0% | 11th 81.3% | 2nd 83.7% | 21st 54.0% | 5th 83.0% | 12th 80.3% | 9th 82.0% | 17th 76.7% | 19th 75.3% | 17th 76.7% | |
| 85.3% | 83% | 82% | 90% | 90% | 82% | 82% | 80% | 89% | 89% | 84% | 89% | 87% | 84% | 85% | 90% | 89% | 79% | 90% | 79% | 85% | 83% | |
| 77.0% | 81% | 83% | 84% | 88% | 81% | 81% | 81% | 76% | 82% | 87% | 83% | 73% | 78% | 84% | 0% | 82% | 80% | 77% | 81% | 74% | 80% | |
| 75.2% | 76% | 85% | 76% | 71% | 69% | 61% | 73% | 83% | 76% | 75% | 85% | 71% | 82% | 82% | 72% | 78% | 82% | 79% | 70% | 67% | 67% |