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 Islam. 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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 9th 81.7% | 2nd 85.7% | 7th 82.0% | 10th 81.3% | 17th 79.7% | 20th 75.7% | 18th 78.3% | 19th 76.3% | 14th 80.3% | 11th 81.0% | 7th 82.0% | 11th 81.0% | 16th 80.0% | 6th 82.3% | 1st 86.0% | 14th 80.3% | 4th 84.3% | 21st 68.3% | 5th 83.7% | 3rd 85.3% | 13th 80.7% | |
| 88.8% | 92% | 94% | 90% | 91% | 76% | 86% | 88% | 80% | 89% | 88% | 88% | 91% | 94% | 92% | 93% | 88% | 94% | 83% | 83% | 92% | 92% | |
| 78.7% | 76% | 86% | 86% | 79% | 89% | 77% | 72% | 69% | 77% | 82% | 79% | 72% | 72% | 75% | 83% | 85% | 75% | 57% | 85% | 89% | 87% | |
| 74.9% | 77% | 77% | 70% | 74% | 74% | 64% | 75% | 80% | 75% | 73% | 79% | 80% | 74% | 80% | 82% | 68% | 84% | 65% | 83% | 75% | 63% |