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 Equally concerned and excited. 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 Haiku 4.5 | Claude Sonnet 4 | Claude Sonnet 4.5 | Gemini 2.5 Flash | Gemma 3 12b It | Llama 4 Maverick | Mistral Medium 3 | GPT 4.1 | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | Qwen3 30b A3B Instruct 2507 | Qwen3 Next 80b A3B Instruct | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Score | 7th 71.7% | 9th 70.0% | 10th 69.7% | 5th 72.3% | 6th 72.0% | 1st 85.5% | 7th 71.7% | 3rd 74.0% | 11th 69.0% | 11th 69.0% | 13th 63.0% | 2nd 78.0% | 4th 73.3% | |
| 90.0% | 84% | 90% | 92% | 85% | 77% | 95% | 94% | 95% | 94% | 94% | 86% | 92% | 92% | |
| 79.1% | 81% | 76% | 76% | 80% | 91% | 76% | 77% | 73% | 76% | 72% | 66% | 92% | 92% | |
| 44.5% | 50% | 44% | 41% | 52% | 48% | 44% | 54% | 37% | 41% | 37% | 50% | 36% |