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 26-35. 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 63.5% | 5th 54.1% | 2nd 73.8% | 4th 62.9% | 6th 42.9% | 1st 81.2% | |
| 65.3% | 56% | 57% | 81% | 77% | 39% | 82% | |
| 75.5% | 84% | 93% | 79% | 78% | 38% | 81% | |
| 59.3% | 62% | 40% | 81% | 45% | 41% | 87% | |
| 58.0% | 65% | 47% | 55% | 55% | 46% | 80% | |
| 64.0% | 62% | 46% | 77% | 64% | 48% | 87% | |
| 70.0% | 70% | 71% | 87% | 73% | 46% | 73% | |
| 27.8% | 18% | 18% | 30% | 19% | 26% | 56% | |
| 69.0% | 63% | 60% | 78% | 84% | 46% | 83% | |
| 75.2% | 91% | 40% | 92% | 75% | 55% | 98% | |
| 66.5% | 64% | 69% | 78% | 59% | 44% | 85% |