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 56-65. 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 80.2% | 3rd 78.4% | 5th 77.4% | 1st 83.3% | 6th 73.4% | 4th 78.2% | |
| 70.7% | 71% | 66% | 69% | 85% | 71% | 62% | |
| 79.0% | 85% | 82% | 73% | 85% | 75% | 74% | |
| 73.2% | 80% | 78% | 72% | 78% | 58% | 73% | |
| 84.7% | 87% | 90% | 85% | 99% | 70% | 77% | |
| 77.8% | 82% | 73% | 78% | 82% | 72% | 80% | |
| 73.5% | 80% | 77% | 76% | 57% | 76% | 75% | |
| 84.8% | 80% | 81% | 81% | 98% | 80% | 89% | |
| 80.2% | 80% | 79% | 81% | 80% | 82% | 79% | |
| 72.2% | 73% | 73% | 71% | 75% | 64% | 77% | |
| 88.8% | 84% | 85% | 88% | 94% | 86% | 96% |