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 Rural. 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 51.7% | 4th 44.3% | 3rd 46.3% | 5th 42.4% | 6th 32.5% | 1st 78.1% | |
| 66.5% | 59% | 76% | 61% | 61% | 58% | 84% | |
| 37.7% | 37% | 38% | 25% | 32% | 14% | 80% | |
| 56.8% | 60% | 57% | 57% | 36% | 37% | 94% | |
| 50.8% | 50% | 39% | 54% | 53% | 21% | 88% | |
| 48.0% | 61% | 57% | 33% | 53% | 8% | 76% | |
| 56.8% | 67% | 50% | 68% | 47% | 26% | 83% | |
| 32.5% | 19% | 3% | 33% | 29% | 54% | 57% | |
| 52.5% | 50% | 47% | 45% | 47% | 44% | 82% | |
| 40.0% | 61% | 24% | 36% | 30% | 24% | 65% | |
| 50.5% | 53% | 52% | 51% | 36% | 39% | 72% |