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 4.1 Fast | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 3rd 77.8% | 1st 83.0% | 8th 73.0% | 6th 76.0% | 2nd 78.8% | 15th 71.0% | 17th 70.5% | 14th 71.5% | 5th 76.3% | 11th 72.3% | 7th 75.3% | 18th 70.2% | 9th 72.8% | 9th 72.8% | 21st 37.3% | 4th 76.5% | 12th 71.8% | 13th 71.7% | 16th 70.8% | 19th 68.5% | 20th 66.0% | |
| 69.5% | 68% | 75% | 70% | 70% | 70% | 59% | 70% | 75% | 64% | 68% | 76% | 79% | 76% | 75% | 73% | 67% | 72% | 66% | 66% | 66% | 54% | |
| 78.9% | 83% | 82% | 78% | 83% | 84% | 74% | 75% | 81% | 83% | 81% | 83% | 74% | 80% | 80% | 76% | 80% | 80% | 74% | 80% | 74% | 72% | |
| 66.3% | 72% | 88% | 76% | 78% | 82% | 66% | 72% | 59% | 77% | 67% | 65% | 58% | 63% | 63% | 0% | 75% | 68% | 65% | 62% | 64% | 73% | |
| 71.7% | 88% | 87% | 68% | 73% | 79% | 85% | 65% | 71% | 81% | 73% | 77% | 70% | 72% | 73% | 0% | 84% | 67% | 82% | 75% | 70% | 65% |