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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 2nd 84.7% | 3rd 84.0% | 14th 79.3% | 9th 81.3% | 19th 77.7% | 15th 79.0% | 17th 78.3% | 21st 76.7% | 9th 81.3% | 16th 78.7% | 8th 81.7% | 11th 81.0% | 3rd 84.0% | 5th 83.3% | 1st 89.0% | 18th 78.3% | 13th 79.7% | 19th 77.7% | 7th 82.3% | 12th 80.0% | 6th 82.7% | |
| 88.9% | 94% | 89% | 90% | 91% | 75% | 91% | 88% | 80% | 89% | 83% | 88% | 91% | 96% | 92% | 99% | 91% | 85% | 88% | 88% | 87% | 92% | |
| 78.7% | 82% | 86% | 79% | 79% | 84% | 77% | 72% | 67% | 77% | 82% | 77% | 72% | 76% | 78% | 87% | 72% | 81% | 78% | 80% | 82% | 85% | |
| 75.3% | 78% | 77% | 69% | 74% | 74% | 69% | 75% | 83% | 78% | 71% | 80% | 80% | 80% | 80% | 81% | 72% | 73% | 67% | 79% | 71% | 71% |