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 GD7 (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 | 1st 86.6% | 2nd 85.9% | 6th 79.3% | 4th 84.9% | 3rd 85.2% | 5th 82.8% | |
| 75.8% | 87% | 70% | 84% | 71% | 71% | 72% | |
| 82.8% | 87% | 87% | 65% | 90% | 89% | 79% | |
| 89.3% | 89% | 90% | 82% | 91% | 99% | 85% | |
| 80.3% | 93% | 81% | 73% | 82% | 71% | 82% | |
| 88.5% | 95% | 87% | 79% | 89% | 90% | 91% | |
| 87.4% | 97% | 75% | 87% | 89% | 89% | ||
| 88.8% | 92% | 92% | 87% | 90% | 85% | 87% | |
| 77.5% | 84% | 79% | 80% | 74% | 79% | 69% | |
| 87.2% | 78% | 93% | 84% | 84% | 96% | 88% | |
| 83.5% | 74% | 83% | 84% | 91% | 83% | 86% |