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 [synth]: Predict response distributions for 56-65. 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 | 2nd 54.6% | 3rd 53.4% | 4th 50.4% | 5th 50.3% | 6th 42.1% | 1st 76.5% | |
| 70.2% | 67% | 77% | 77% | 75% | 45% | 80% | |
| 46.5% | 48% | 44% | 44% | 43% | 22% | 78% | |
| 56.7% | 51% | 54% | 55% | 52% | 39% | 89% | |
| 47.0% | 45% | 32% | 46% | 43% | 44% | 72% | |
| 46.0% | 37% | 52% | 0% | 60% | 52% | 75% | |
| 65.8% | 75% | 56% | 75% | 52% | 53% | 84% | |
| 28.3% | 24% | 31% | 33% | 20% | 16% | 46% | |
| 65.0% | 67% | 70% | 60% | 60% | 54% | 79% | |
| 53.8% | 68% | 36% | 50% | 35% | 48% | 86% | |
| 66.2% | 64% | 82% | 64% | 63% | 48% | 76% |