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 Suburban. 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 61.2% | 5th 59.8% | 3rd 66.0% | 2nd 72.2% | 6th 49.5% | 1st 82.2% | |
| 66.5% | 61% | 61% | 81% | 79% | 40% | 77% | |
| 76.8% | 73% | 80% | 82% | 78% | 69% | 79% | |
| 59.0% | 60% | 42% | 58% | 63% | 44% | 87% | |
| 65.2% | 69% | 61% | 61% | 60% | 50% | 90% | |
| 65.5% | 60% | 62% | 61% | 81% | 52% | 77% | |
| 76.5% | 71% | 85% | 86% | 85% | 50% | 82% | |
| 32.3% | 19% | 19% | 32% | 31% | 31% | 62% | |
| 73.3% | 68% | 68% | 81% | 90% | 48% | 85% | |
| 64.3% | 71% | 44% | 48% | 75% | 56% | 92% | |
| 72.0% | 60% | 76% | 70% | 80% | 55% | 91% |