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 Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | Qwen3 30b A3B Instruct 2507 | Qwen3 Next 80b A3B Instruct | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 1st 82.0% | 6th 77.0% | 5th 77.7% | 3rd 79.3% | 10th 73.0% | 11th 72.3% | 7th 76.0% | 9th 73.3% | 4th 78.3% | 13th 67.7% | 8th 75.3% | 11th 72.3% | 2nd 80.3% | |
| 82.1% | 86% | 88% | 79% | 85% | 86% | 71% | 87% | 81% | 83% | 77% | 79% | 74% | 91% | |
| 72.3% | 86% | 75% | 80% | 78% | 69% | 71% | 73% | 68% | 72% | 58% | 62% | 72% | 76% | |
| 72.8% | 74% | 68% | 74% | 75% | 64% | 75% | 68% | 71% | 80% | 68% | 85% | 71% | 74% |