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 excited than concerned. Source: Global Dialogues GD5 (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 | 3rd 83.8% | 2nd 85.9% | 1st 86.5% | 4th 81.4% | 6th 77.9% | 5th 79.1% | |
| 88.2% | 88% | 88% | 89% | 88% | 88% | 88% | |
| 80.0% | 77% | 92% | 94% | 83% | 63% | 71% | |
| 76.3% | 80% | 77% | 86% | 78% | 73% | 64% | |
| 94.5% | 95% | 95% | 94% | 95% | 94% | 94% | |
| 89.7% | 92% | 83% | 90% | 89% | 89% | 95% | |
| 93.3% | 96% | 96% | 78% | 98% | 96% | 96% | |
| 84.2% | 85% | 89% | 91% | 78% | 84% | 78% | |
| 86.5% | 92% | 87% | 89% | 90% | 73% | 88% | |
| 62.5% | 62% | 70% | 79% | 49% | 54% | 61% | |
| 69.2% | 71% | 82% | 75% | 66% | 65% | 56% |