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 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 84.8% | 6th 71.8% | 3rd 82.1% | 2nd 83.6% | 4th 80.5% | 5th 75.6% | |
| 75.8% | 84% | 50% | 82% | 75% | 91% | 73% | |
| 78.3% | 87% | 73% | 73% | 84% | 75% | 78% | |
| 87.8% | 83% | 93% | 88% | 93% | 83% | 87% | |
| 78.3% | 83% | 59% | 79% | 87% | 87% | 75% | |
| 82.5% | 90% | 90% | 84% | 86% | 75% | 70% | |
| 80.0% | 88% | 75% | 83% | 82% | 76% | 76% | |
| 76.0% | 83% | 82% | 86% | 79% | 62% | 64% | |
| 70.5% | 75% | 60% | 76% | 72% | 77% | 63% | |
| 83.7% | 94% | 65% | 85% | 87% | 90% | 81% | |
| 84.3% | 81% | 71% | 85% | 91% | 89% | 89% |