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 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 76.7% | 3rd 77.8% | 6th 70.8% | 2nd 78.7% | 1st 80.9% | 5th 75.2% | |
| 89.8% | 95% | 93% | 81% | 90% | 93% | 87% | |
| 73.5% | 64% | 71% | 70% | 88% | 79% | 69% | |
| 88.8% | 88% | 92% | 84% | 89% | 94% | 86% | |
| 82.0% | 81% | 82% | 81% | 85% | 81% | 82% | |
| 68.2% | 68% | 76% | 57% | 77% | 72% | 59% | |
| 84.5% | 87% | 88% | 73% | 88% | 85% | 86% | |
| 51.7% | 56% | 33% | 68% | 35% | 55% | 63% | |
| 74.7% | 78% | 82% | 53% | 79% | 87% | 69% | |
| 74.8% | 70% | 75% | 76% | 75% | 80% | 73% | |
| 78.8% | 80% | 86% | 65% | 81% | 83% | 78% |