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 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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 9th 77.5% | 4th 80.8% | 2nd 81.5% | 6th 79.3% | 11th 75.8% | 19th 70.3% | 14th 75.3% | 3rd 81.3% | 11th 75.8% | 14th 75.3% | 1st 82.8% | 5th 79.8% | 11th 75.8% | 7th 79.0% | 10th 77.3% | 8th 78.8% | 17th 72.0% | 18th 71.3% | 16th 74.0% | 19th 70.3% | 21st 69.5% | |
| 80.0% | 83% | 90% | 80% | 80% | 73% | 61% | 73% | 92% | 81% | 76% | 90% | 93% | 80% | 88% | 74% | 86% | 77% | 79% | 74% | 79% | 70% | |
| 66.3% | 64% | 72% | 74% | 65% | 70% | 67% | 75% | 72% | 64% | 61% | 75% | 71% | 70% | 66% | 66% | 67% | 54% | 63% | 66% | 58% | 53% | |
| 77.0% | 82% | 80% | 85% | 86% | 81% | 74% | 73% | 70% | 75% | 80% | 79% | 77% | 73% | 79% | 86% | 79% | 76% | 58% | 81% | 67% | 76% | |
| 82.0% | 81% | 81% | 87% | 86% | 79% | 79% | 80% | 91% | 83% | 84% | 87% | 78% | 80% | 83% | 83% | 83% | 81% | 85% | 75% | 77% | 79% |