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 | 5th 78.3% | 1st 82.3% | 4th 79.0% | 2nd 80.7% | 3rd 80.0% | 13th 73.0% | 14th 72.3% | 14th 72.3% | 9th 74.7% | 8th 75.7% | 6th 76.0% | 19th 67.7% | 7th 75.7% | 11th 73.7% | 21st 54.3% | 10th 74.7% | 16th 72.0% | 16th 72.0% | 11th 73.7% | 20th 65.3% | 18th 70.7% | |
| 82.3% | 86% | 86% | 88% | 88% | 89% | 86% | 71% | 86% | 87% | 82% | 87% | 77% | 78% | 79% | 87% | 83% | 82% | 87% | 81% | 63% | 76% | |
| 66.1% | 72% | 87% | 75% | 80% | 76% | 69% | 71% | 60% | 73% | 73% | 63% | 59% | 69% | 62% | 0% | 74% | 61% | 57% | 72% | 63% | 72% | |
| 72.1% | 77% | 74% | 74% | 74% | 75% | 64% | 75% | 71% | 64% | 72% | 78% | 67% | 80% | 80% | 76% | 67% | 73% | 72% | 68% | 70% | 64% |