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 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 4th 78.0% | 1st 82.0% | 7th 77.0% | 5th 77.7% | 2nd 80.3% | 13th 73.0% | 15th 72.3% | 18th 71.3% | 3rd 79.7% | 9th 74.3% | 6th 77.3% | 17th 71.7% | 12th 73.0% | 11th 73.7% | 8th 75.0% | 10th 74.0% | 19th 69.7% | 14th 72.7% | 15th 72.3% | 20th 65.3% | |
| 81.6% | 88% | 86% | 88% | 79% | 89% | 86% | 71% | 79% | 87% | 82% | 89% | 77% | 77% | 79% | 84% | 84% | 82% | 88% | 74% | 63% | |
| 69.2% | 72% | 86% | 75% | 80% | 77% | 69% | 71% | 59% | 73% | 69% | 64% | 57% | 62% | 62% | 80% | 74% | 61% | 57% | 72% | 63% | |
| 72.8% | 74% | 74% | 68% | 74% | 75% | 64% | 75% | 76% | 79% | 72% | 79% | 81% | 80% | 80% | 61% | 64% | 66% | 73% | 71% | 70% |