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 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 | 4th 76.2% | 2nd 76.9% | 5th 76.0% | 1st 77.7% | 2nd 76.9% | 6th 70.0% | |
| 76.2% | 65% | 80% | 84% | 80% | 86% | 62% | |
| 65.0% | 69% | 72% | 72% | 63% | 55% | 59% | |
| 70.5% | 72% | 58% | 57% | 83% | 77% | 76% | |
| 86.8% | 81% | 91% | 90% | 93% | 85% | 81% | |
| 88.0% | 86% | 92% | 85% | 83% | 91% | 91% | |
| 74.8% | 70% | 76% | 74% | 74% | 89% | 66% | |
| 52.8% | 60% | 58% | 55% | 45% | 57% | 42% | |
| 74.5% | 84% | 69% | 77% | 82% | 61% | 74% | |
| 88.8% | 94% | 89% | 86% | 90% | 89% | 85% | |
| 78.7% | 81% | 84% | 80% | 84% | 79% | 64% |