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 26-35. 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 | 2nd 84.3% | 1st 85.3% | 4th 82.2% | 3rd 82.4% | 5th 81.0% | 6th 80.2% | |
| 82.2% | 91% | 81% | 80% | 78% | 82% | 81% | |
| 87.3% | 88% | 88% | 87% | 87% | 89% | 85% | |
| 78.5% | 83% | 82% | 78% | 77% | 68% | 83% | |
| 69.7% | 64% | 76% | 75% | 76% | 61% | 66% | |
| 90.5% | 91% | 95% | 83% | 94% | 91% | 89% | |
| 79.0% | 80% | 80% | 79% | 83% | 75% | 77% | |
| 87.7% | 84% | 94% | 91% | 84% | 88% | 85% | |
| 88.5% | 92% | 88% | 81% | 88% | 95% | 87% | |
| 78.0% | 78% | 84% | 81% | 73% | 75% | 77% | |
| 84.3% | 92% | 85% | 87% | 84% | 86% | 72% |