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 18-25. 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 61.6% | 5th 54.1% | 3rd 61.4% | 4th 57.0% | 6th 45.6% | 1st 82.3% | |
| 58.7% | 58% | 61% | 59% | 56% | 39% | 79% | |
| 66.2% | 77% | 61% | 73% | 73% | 33% | 80% | |
| 54.8% | 57% | 40% | 63% | 43% | 42% | 84% | |
| 59.2% | 65% | 54% | 54% | 54% | 45% | 83% | |
| 63.7% | 64% | 48% | 66% | 68% | 51% | 85% | |
| 67.7% | 67% | 66% | 67% | 66% | 62% | 78% | |
| 26.3% | 22% | 16% | 23% | 17% | 26% | 54% | |
| 68.0% | 62% | 67% | 73% | 51% | 62% | 93% | |
| 79.2% | 87% | 72% | 83% | 85% | 54% | 94% | |
| 59.7% | 57% | 56% | 53% | 57% | 42% | 93% |