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 79.7% | 3rd 78.3% | 11th 73.5% | 1st 80.0% | 5th 78.0% | 14th 72.5% | 16th 70.3% | 12th 72.8% | 6th 76.5% | 10th 73.5% | 4th 78.3% | 19th 68.2% | 15th 71.8% | 12th 72.8% | 7th 76.0% | 8th 75.3% | 9th 74.8% | 17th 70.0% | 20th 68.0% | 21st 60.0% | 18th 69.0% | |
| 69.3% | 74% | 70% | 70% | 70% | 69% | 59% | 70% | 75% | 65% | 68% | 76% | 71% | 70% | 75% | 68% | 67% | 71% | 72% | 66% | 62% | 67% | |
| 78.1% | 83% | 82% | 76% | 83% | 89% | 76% | 75% | 81% | 85% | 81% | 80% | 74% | 78% | 80% | 77% | 80% | 77% | 68% | 76% | 60% | 80% | |
| 69.7% | 74% | 76% | 76% | 81% | 75% | 70% | 71% | 62% | 75% | 70% | 74% | 58% | 71% | 63% | 78% | 76% | 74% | 57% | 62% | 58% | 62% | |
| 76.0% | 88% | 85% | 72% | 86% | 79% | 85% | 65% | 73% | 81% | 75% | 83% | 70% | 68% | 73% | 81% | 78% | 77% | 83% | 68% | 60% | 67% |