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 Urban. 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 62.8% | 5th 54.7% | 2nd 67.0% | 3rd 65.0% | 6th 42.8% | 1st 82.3% | |
| 69.8% | 60% | 77% | 82% | 79% | 40% | 81% | |
| 66.7% | 88% | 40% | 81% | 78% | 34% | 79% | |
| 61.5% | 77% | 59% | 58% | 46% | 42% | 87% | |
| 61.8% | 64% | 53% | 55% | 65% | 49% | 85% | |
| 68.5% | 64% | 61% | 76% | 73% | 54% | 83% | |
| 64.0% | 69% | 53% | 70% | 69% | 42% | 81% | |
| 25.2% | 19% | 12% | 30% | 20% | 18% | 52% | |
| 69.7% | 54% | 65% | 69% | 76% | 64% | 90% | |
| 74.0% | 75% | 67% | 89% | 84% | 35% | 94% | |
| 63.2% | 58% | 60% | 60% | 60% | 50% | 91% |