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 Female. Source: Global Dialogues GD2 (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 | 14th 76.7% | 4th 79.7% | 10th 78.0% | 3rd 79.7% | 1st 80.0% | 20th 73.7% | 18th 75.7% | 11th 77.7% | 6th 79.0% | 9th 78.7% | 12th 77.3% | 2nd 80.0% | 16th 76.3% | 6th 79.0% | 13th 77.0% | 5th 79.3% | 21st 72.3% | 16th 76.3% | 6th 79.0% | 19th 75.5% | 14th 76.7% | |
| 90.5% | 86% | 91% | 91% | 91% | 92% | 85% | 88% | 94% | 97% | 96% | 91% | 88% | 93% | 92% | 95% | 91% | 83% | 88% | 92% | 83% | 94% | |
| 69.7% | 73% | 74% | 75% | 80% | 72% | 68% | 71% | 62% | 67% | 69% | 63% | 73% | 60% | 58% | 79% | 80% | 59% | 67% | 72% | 72% | ||
| 72.0% | 71% | 74% | 68% | 68% | 76% | 68% | 68% | 77% | 73% | 71% | 78% | 79% | 76% | 87% | 57% | 67% | 75% | 74% | 73% | 68% | 64% |