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 | 3rd 58.9% | 4th 58.3% | 6th 54.6% | 2nd 62.7% | 5th 55.3% | 1st 78.5% | |
| 69.7% | 68% | 72% | 59% | 78% | 57% | 84% | |
| 57.2% | 56% | 50% | 50% | 60% | 52% | 75% | |
| 59.0% | 52% | 54% | 54% | 54% | 52% | 88% | |
| 56.0% | 53% | 38% | 46% | 44% | 83% | 72% | |
| 54.5% | 49% | 51% | 37% | 62% | 52% | 76% | |
| 77.7% | 75% | 75% | 77% | 77% | 74% | 88% | |
| 35.8% | 18% | 31% | 49% | 31% | 31% | 55% | |
| 70.2% | 69% | 71% | 58% | 85% | 54% | 84% | |
| 64.2% | 67% | 59% | 52% | 71% | 49% | 87% | |
| 69.7% | 82% | 82% | 64% | 65% | 49% | 76% |