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 88.5% | 3rd 88.0% | 9th 85.8% | 10th 85.5% | 18th 80.0% | 21st 78.5% | 17th 81.0% | 18th 80.0% | 13th 83.5% | 6th 86.3% | 12th 84.8% | 20th 79.3% | 5th 86.5% | 11th 85.3% | 3rd 88.0% | 8th 85.8% | 16th 81.0% | 14th 82.5% | 7th 86.0% | 15th 82.0% | 1st 90.2% | |
| 75.0% | 79% | 72% | 63% | 70% | 74% | 59% | 70% | 76% | 66% | 75% | 84% | 78% | 83% | 85% | 81% | 77% | 76% | 73% | 73% | 76% | 84% | |
| 87.9% | 95% | 91% | 90% | 92% | 88% | 83% | 91% | 88% | 88% | 91% | 89% | 80% | 90% | 93% | 84% | 86% | 82% | 80% | 86% | 84% | 94% | |
| 87.2% | 92% | 96% | 94% | 89% | 94% | 83% | 78% | 81% | 92% | 92% | 81% | 74% | 84% | 78% | 94% | 91% | 78% | 90% | 96% | 79% | 95% | |
| 86.8% | 88% | 93% | 96% | 91% | 64% | 89% | 85% | 75% | 88% | 87% | 85% | 85% | 89% | 85% | 93% | 89% | 88% | 87% | 89% | 89% | 88% |