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 GD4 (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 | 2nd 78.1% | 1st 82.7% | 4th 76.6% | 5th 73.3% | 6th 69.1% | 3rd 77.6% | |
| 78.8% | 77% | 84% | 86% | 80% | 64% | 82% | |
| 47.0% | 61% | 59% | 44% | 37% | 37% | 44% | |
| 78.5% | 79% | 78% | 89% | 75% | 77% | 73% | |
| 77.7% | 80% | 85% | 78% | 71% | 68% | 84% | |
| 88.2% | 90% | 96% | 82% | 86% | 88% | 87% | |
| 83.0% | 86% | 86% | 95% | 84% | 60% | 87% | |
| 55.0% | 47% | 68% | 50% | 47% | 59% | 59% | |
| 81.8% | 83% | 88% | 81% | 81% | 76% | 82% | |
| 87.3% | 82% | 93% | 86% | 87% | 88% | 88% | |
| 85.0% | 96% | 90% | 75% | 85% | 74% | 90% |