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 More concerned than excited. 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 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 | 5th 77.5% | 6th 77.3% | 1st 83.5% | 13th 64.5% | 7th 77.3% | 2nd 82.8% | 4th 79.3% | 2nd 82.8% | 9th 74.5% | 10th 73.0% | 11th 70.8% | 8th 76.3% | 12th 68.3% | |
| 63.3% | 54% | 57% | 69% | 76% | 51% | 100% | 46% | 67% | 55% | 100% | 55% | 47% | 46% | |
| 86.9% | 83% | 91% | 99% | 81% | 91% | 90% | 97% | 96% | 88% | 68% | 83% | 89% | 74% | |
| 64.9% | 76% | 76% | 76% | 46% | 73% | 55% | 77% | 75% | 58% | 38% | 54% | 76% | 64% | |
| 88.7% | 97% | 85% | 90% | 55% | 94% | 86% | 97% | 93% | 97% | 86% | 91% | 93% | 89% |