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 GD7 (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 | Gemini 2.5 Flash | Gemma 3 12b It | GPT 4.1 Mini | GPT 4.1 Nano | GPT 4o Mini | |
|---|---|---|---|---|---|---|---|
| Score | 1st 87.9% | 2nd 87.2% | 5th 83.1% | 3rd 86.3% | 4th 83.3% | 6th 82.3% | |
| 89.3% | 96% | 90% | 90% | 98% | 81% | 81% | |
| 78.8% | 82% | 76% | 86% | 78% | 78% | 73% | |
| 84.8% | 83% | 95% | 76% | 85% | 91% | 79% | |
| 88.0% | 96% | 93% | 78% | 87% | 87% | 87% | |
| 90.5% | 88% | 93% | 92% | 90% | 85% | 95% | |
| 85.8% | 90% | 92% | 79% | 87% | 88% | 79% | |
| 86.2% | 88% | 87% | 88% | 89% | 77% | 88% | |
| 72.0% | 82% | 71% | 73% | 77% | 70% | 59% | |
| 88.0% | 86% | 93% | 82% | 81% | 90% | 96% | |
| 86.7% | 88% | 82% | 87% | 91% | 86% | 86% |