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 59.2% | 5th 53.6% | 4th 54.5% | 3rd 57.0% | 6th 49.3% | 1st 82.3% | |
| 60.8% | 58% | 72% | 59% | 59% | 38% | 79% | |
| 71.2% | 75% | 53% | 74% | 76% | 67% | 82% | |
| 55.5% | 44% | 39% | 82% | 43% | 43% | 82% | |
| 59.7% | 65% | 54% | 54% | 54% | 45% | 86% | |
| 53.2% | 53% | 48% | 0% | 67% | 66% | 85% | |
| 65.8% | 67% | 66% | 67% | 67% | 48% | 80% | |
| 19.8% | 22% | 16% | 0% | 17% | 14% | 50% | |
| 67.2% | 62% | 62% | 73% | 50% | 64% | 92% | |
| 78.2% | 88% | 70% | 83% | 80% | 54% | 94% | |
| 61.8% | 58% | 56% | 53% | 57% | 54% | 93% |