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 GD1 (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 88.0% | 7th 86.0% | 4th 87.3% | 5th 86.5% | 18th 80.0% | 20th 79.3% | 15th 81.5% | 17th 80.3% | 10th 85.0% | 6th 86.3% | 9th 85.5% | 21st 75.8% | 1st 88.3% | 14th 83.0% | 2nd 88.0% | 8th 85.8% | 19th 79.8% | 10th 85.0% | 12th 84.8% | 16th 80.5% | 13th 84.7% | |
| 73.9% | 76% | 72% | 65% | 70% | 69% | 59% | 70% | 79% | 70% | 75% | 84% | 58% | 85% | 84% | 83% | 77% | 76% | 75% | 73% | 76% | 76% | |
| 88.9% | 96% | 86% | 92% | 92% | 90% | 86% | 89% | 87% | 91% | 90% | 85% | 86% | 94% | 93% | 89% | 86% | 85% | 86% | 86% | 84% | 94% | |
| 86.5% | 89% | 96% | 94% | 89% | 91% | 83% | 82% | 81% | 92% | 91% | 85% | 74% | 85% | 78% | 93% | 92% | 77% | 89% | 95% | 73% | 87% | |
| 86.1% | 91% | 90% | 98% | 95% | 70% | 89% | 85% | 74% | 87% | 89% | 88% | 85% | 89% | 77% | 87% | 88% | 81% | 90% | 85% | 89% | 82% |