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 | 1st 75.7% | 7th 67.3% | 4th 71.0% | 2nd 73.0% | 6th 68.0% | 5th 69.3% | 10th 65.0% | 10th 65.0% | 9th 65.0% | 12th 64.7% | 12th 64.7% | 8th 66.0% | 3rd 72.3% | |
| 85.6% | 90% | 83% | 86% | 83% | 84% | 87% | 82% | 75% | 91% | 87% | 86% | 86% | 93% | |
| 70.7% | 76% | 75% | 80% | 77% | 76% | 59% | 69% | 63% | 63% | 70% | 64% | 71% | 76% | |
| 48.4% | 61% | 44% | 47% | 59% | 44% | 62% | 44% | 57% | 41% | 37% | 44% | 41% | 48% |