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: Predict response distributions for 26-35. Source: Global Dialogues GD6 (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 | 6th 76.4% | 1st 83.4% | 4th 81.6% | 2nd 82.3% | 5th 78.0% | 3rd 82.2% | |
| 86.7% | 79% | 95% | 89% | 85% | 86% | 86% | |
| 65.2% | 10% | 82% | 65% | 83% | 74% | 77% | |
| 84.2% | 89% | 81% | 76% | 84% | 85% | 90% | |
| 80.8% | 71% | 67% | 85% | 90% | 91% | 81% | |
| 84.3% | 93% | 86% | 64% | 85% | 85% | 93% | |
| 85.8% | 87% | 92% | 98% | 87% | 69% | 82% | |
| 85.7% | 86% | 92% | 86% | 84% | 81% | 85% | |
| 74.7% | 84% | 81% | 80% | 71% | 63% | 69% | |
| 84.8% | 92% | 83% | 79% | 91% | 77% | 87% | |
| 74.3% | 73% | 75% | 94% | 63% | 69% | 72% |