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 46-55. 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 81.6% | 2nd 84.5% | 6th 77.3% | 1st 86.2% | 5th 78.4% | 4th 79.1% | |
| 70.7% | 67% | 75% | 68% | 80% | 71% | 63% | |
| 83.7% | 83% | 90% | 77% | 86% | 85% | 81% | |
| 83.3% | 86% | 85% | 78% | 89% | 81% | 81% | |
| 77.5% | 86% | 90% | 64% | 89% | 60% | 76% | |
| 90.2% | 94% | 88% | 88% | 94% | 88% | 89% | |
| 74.0% | 77% | 76% | 75% | 71% | 74% | 71% | |
| 83.3% | 78% | 88% | 86% | 89% | 81% | 78% | |
| 79.7% | 87% | 74% | 68% | 87% | 84% | 78% | |
| 82.5% | 77% | 93% | 76% | 84% | 79% | 86% | |
| 87.0% | 81% | 86% | 93% | 93% | 81% | 88% |