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 | 9th 71.7% | 11th 70.0% | 10th 71.3% | 4th 73.7% | 4th 73.7% | 1st 78.3% | 8th 72.0% | 3rd 74.0% | 7th 73.0% | 13th 61.7% | 12th 64.7% | 2nd 78.0% | 6th 73.3% | |
| 89.5% | 84% | 91% | 92% | 85% | 77% | 95% | 94% | 95% | 99% | 82% | 86% | 92% | 92% | |
| 79.1% | 81% | 76% | 76% | 79% | 90% | 75% | 78% | 73% | 76% | 73% | 67% | 92% | 92% | |
| 47.2% | 50% | 43% | 46% | 57% | 54% | 65% | 44% | 54% | 44% | 30% | 41% | 50% | 36% |