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 GD3 (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 80.7% | 4th 80.1% | 5th 76.8% | 3rd 80.3% | 6th 73.2% | 1st 81.3% | |
| 79.3% | 78% | 82% | 83% | 78% | 77% | 78% | |
| 79.5% | 81% | 94% | 74% | 88% | 56% | 84% | |
| 72.7% | 74% | 67% | 74% | 70% | 75% | 76% | |
| 81.2% | 91% | 83% | 80% | 83% | 72% | 78% | |
| 55.5% | 56% | 65% | 43% | 62% | 54% | 53% | |
| 86.3% | 81% | 90% | 89% | 80% | 92% | 86% | |
| 85.8% | 82% | 90% | 85% | 85% | 87% | 86% | |
| 86.3% | 89% | 86% | 86% | 89% | 80% | 88% | |
| 77.5% | 83% | 68% | 82% | 80% | 59% | 93% | |
| 83.2% | 92% | 76% | 72% | 88% | 80% | 91% |