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 | 4th 76.0% | 1st 79.5% | 8th 75.0% | 5th 76.0% | 2nd 78.3% | 14th 72.0% | 17th 70.5% | 12th 73.8% | 7th 75.8% | 13th 72.8% | 3rd 76.3% | 20th 67.3% | 11th 73.8% | 10th 74.0% | 6th 75.8% | 9th 75.0% | 18th 68.5% | 16th 70.8% | 15th 71.0% | 19th 68.3% | 21st 66.0% | |
| 67.7% | 67% | 75% | 63% | 70% | 70% | 59% | 71% | 75% | 65% | 64% | 76% | 67% | 76% | 75% | 66% | 66% | 61% | 68% | 66% | 63% | 59% | |
| 78.7% | 77% | 82% | 76% | 83% | 83% | 74% | 75% | 86% | 83% | 81% | 83% | 74% | 80% | 80% | 79% | 80% | 74% | 70% | 84% | 74% | 74% | |
| 69.0% | 72% | 76% | 76% | 78% | 81% | 70% | 71% | 61% | 74% | 71% | 65% | 58% | 63% | 64% | 78% | 76% | 62% | 62% | 62% | 65% | 64% | |
| 77.2% | 88% | 85% | 85% | 73% | 79% | 85% | 65% | 73% | 81% | 75% | 81% | 70% | 76% | 77% | 80% | 78% | 77% | 83% | 72% | 71% | 67% |