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 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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 87.0% | 6th 86.5% | 8th 86.5% | 9th 85.5% | 18th 80.8% | 21st 77.3% | 19th 80.5% | 20th 79.5% | 17th 81.3% | 13th 84.3% | 10th 85.5% | 14th 83.5% | 2nd 87.3% | 15th 83.3% | 1st 88.0% | 12th 84.5% | 10th 85.5% | 16th 83.0% | 6th 86.5% | 4th 86.8% | 4th 86.8% | |
| 74.0% | 73% | 72% | 64% | 70% | 71% | 59% | 70% | 78% | 66% | 68% | 82% | 79% | 83% | 81% | 76% | 73% | 79% | 74% | 72% | 79% | 84% | |
| 87.8% | 94% | 86% | 90% | 92% | 88% | 78% | 89% | 86% | 79% | 92% | 88% | 86% | 93% | 93% | 90% | 85% | 86% | 86% | 86% | 82% | 94% | |
| 88.0% | 88% | 95% | 94% | 89% | 95% | 83% | 78% | 80% | 92% | 91% | 84% | 78% | 84% | 82% | 94% | 91% | 92% | 81% | 95% | 94% | 87% | |
| 87.4% | 93% | 93% | 98% | 91% | 69% | 89% | 85% | 74% | 88% | 86% | 88% | 91% | 89% | 77% | 92% | 89% | 85% | 91% | 93% | 92% | 82% |