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 | 6th 79.0% | 1st 85.0% | 8th 76.0% | 4th 80.7% | 2nd 83.0% | 15th 73.0% | 17th 72.3% | 7th 76.7% | 10th 74.3% | 10th 74.3% | 5th 79.7% | 18th 70.0% | 14th 73.0% | 13th 73.7% | 3rd 81.7% | 8th 76.0% | 19th 69.0% | 15th 73.0% | 20th 68.0% | 21st 66.0% | 12th 74.0% | |
| 82.1% | 88% | 89% | 79% | 88% | 91% | 86% | 71% | 86% | 87% | 80% | 88% | 77% | 77% | 79% | 84% | 81% | 82% | 88% | 74% | 76% | 73% | |
| 70.2% | 72% | 87% | 75% | 80% | 83% | 69% | 71% | 75% | 72% | 69% | 72% | 57% | 62% | 62% | 82% | 72% | 61% | 58% | 60% | 63% | 72% | |
| 73.2% | 77% | 79% | 74% | 74% | 75% | 64% | 75% | 69% | 64% | 74% | 79% | 76% | 80% | 80% | 79% | 75% | 64% | 73% | 70% | 59% | 77% |